{"schema_version":"onlylabs.public_analysis_evidence.v1","title":"SambaNova Systems analysis evidence pack","description":"Public onlylabs evidence pack for cited agent analysis: captured pages, ranked public signals, and stored web-search provenance used by the background analysis workflow.","url":"https://onlylabs.fyi/labs/sambanova","json_url":"https://onlylabs.fyi/analysis/sambanova/evidence.json","generated_at":"2026-06-11T16:53:26.515Z","org":{"slug":"sambanova","name":"SambaNova Systems","category":"neocloud","category_label":"Neocloud","dossier_url":"https://onlylabs.fyi/labs/sambanova"},"analysis":null,"workflow":{"version":"onlylabs-deepagents-analysis-v3","provider":null,"model":null,"agent":null,"public_pack_mode":"local-pages-and-events","live_web_fetches":false,"note":"Public evidence exports do not trigger live Exa calls; stored Exa provenance is included when analysis metadata contains it."},"stats":{"pages":28,"events":71,"web":0,"evidence":88,"signal_desks":{"hiring":20,"forks":2,"releases":12,"talking":11,"repos":15},"data_radar_lanes":null,"data_radar_matches":null,"stored_analysis_evidence":null,"stored_analysis_web":null,"stored_analysis_signal_desks":null,"stored_analysis_data_radar_lanes":null,"stored_analysis_data_radar_matches":null},"stored_web_provenance":null,"evidence":[{"ref":"P1","kind":"page","title":"Gemma 4 31B Runs Fastest on SambaCloud","date":"2026-06-11T07:04:02.104371+00:00","date_source":null,"source_url":"https://sambanova.ai/blog/gemma-4-31b-running-fastest-on-sambacloud","signal_url":null,"signal_json_url":null,"text":"Gemma 4 31B Runs Fastest on SambaCloud \n\nBACK TO RESOURCES\n\nBlog \n\nGemma 4 31B Running Fastest on SambaCloud \n\nby SambaNova \n\n--> \nJune 10, 2026\n\nGemma 4 31B is Google DeepMind's most capable dense open model to date — and it's running fastest on SambaCloud. Try it today for reasoning, coding, and agentic workflows on SambaCloud .\n\nGemma 4 31B is an open-weight (Apache 2.0) frontier dense model built for advanced reasoning, coding, and agentic workflows\n\nTop benchmarks: 85.2% MMLU Pro, 89.2% AIME 2026 (no tools), 80.0% LiveCodeBench v6, 84.3% GPQA Diamond, Codeforces ELO 2150\n\nGemma 4 31B is an open multimodal model and supports text and image input with text output.\n\nAvailable as a preview model on SambaCloud playground or API with the model name gemma-4-31B-it\n\nIt's the largest dense model in Google's Gemma 4 family, built from the same research foundation as Gemini 3.\n\nRead the official Gemma 4 announcement here. \n\nSambaCloud runs Gemma 4 31B more than 30% faster than the next provider and miles ahead of the rest. The fastest place to run Gemma 4 31B, verified by Artificial Analysis . \n\nWhy Use Gemma 4 31B? \n\nGemma 4 31B brings frontier-class reasoning to an open-weight model that's small enough to fine-tune and deploy on accessible hardware, while SambaCloud delivers it at the lowest latency available. Key strengths include:\n\nAdvanced Reasoning\n\nBuilt as a highly capable reasoner with a configurable thinking mode, Gemma 4 31B scores 89.2% on AIME 2026 (no tools) and 84.3% on GPQA Diamond, with strong multi-step planning and instruction-following. Toggle thinking on or off depending on whether your workload needs deep deliberation or fast turnaround.\n\nState-of-the-Art Coding\n\nProduction-grade coding performance with 80.0% on LiveCodeBench v6 and a Codeforces ELO of 2150 — turning a single workstation, or a SambaCloud endpoint, into a frontier-class local-first code assistant.\n\nNative Agentic Capabilities \n\nNative function-calling, structured JSON output, and native system-prompt support let you build autonomous agents that reliably interact with tools and APIs. Pairs naturally with multi-agent frameworks like OpenClaw and CrewAI.\n\nGet Started Quickly with Sam"},{"ref":"P2","kind":"page","title":"sambanova/lm-evaluation-harness repository metadata","date":"2026-06-11T04:19:35.414643+00:00","date_source":null,"source_url":"https://github.com/sambanova/lm-evaluation-harness","signal_url":null,"signal_json_url":null,"text":"# sambanova/lm-evaluation-harness\n\nDescription: A framework for few-shot evaluation of language models.\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 3\n\nForks: 0\n\nOpen issues: 1\n\nCreated: 2024-03-08T16:10:36Z\n\nPushed: 2024-05-17T20:08:23Z\n\nDefault branch: main\n\nFork: yes\n\nParent repository: EleutherAI/lm-evaluation-harness\n\nArchived: no\n\nREADME:\n# Language Model Evaluation Harness\n\n[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.10256836.svg)](https://doi.org/10.5281/zenodo.10256836)\n\n## Announcement\n**A new v0.4.0 release of lm-evaluation-harness is available** !\n\nNew updates and features include:\n\n- Internal refactoring\n- Config-based task creation and configuration\n- Easier import and sharing of externally-defined task config YAMLs\n- Support for Jinja2 prompt design, easy modification of prompts + prompt imports from Promptsource\n- More advanced configuration options, including output post-processing, answer extraction, and multiple LM generations per document, configurable fewshot settings, and more\n- Speedups and new modeling libraries supported, including: faster data-parallel HF model usage, vLLM support, MPS support with HuggingFace, and more\n- Logging and usability changes\n- New tasks including CoT BIG-Bench-Hard, Belebele, user-defined task groupings, and more\n\nPlease see our updated documentation pages in `docs/` for more details.\n\nDevelopment will be continuing on the `main` branch, and we encourage you to give us feedback on what features are desired and how to improve the library further, or ask questions, either in issues or PRs on GitHub, or in the [EleutherAI discord](https://discord.gg/eleutherai)!\n\n## Overview\n\nThis project provides a unified framework to test generative language models on a large number of different evaluation tasks.\n\n**Features:**\n- Over 60 standard academic benchmarks for LLMs, with hundreds of subtasks and variants implemented.\n- Support for models loaded via [transformers](https://github.com/huggingface/transformers/) (including quantization via [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ)), [GPT-NeoX](https://github.com/EleutherAI/gpt-neox), and [Megatron-DeepSpeed](https://github.com/microsoft/Megatron-DeepSpeed/), wi"},{"ref":"P3","kind":"page","title":"sambanova/generative_data_prep repository metadata","date":"2026-06-11T04:10:35.230398+00:00","date_source":null,"source_url":"https://github.com/sambanova/generative_data_prep","signal_url":null,"signal_json_url":null,"text":"# sambanova/generative_data_prep\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 67\n\nForks: 10\n\nOpen issues: 7\n\nCreated: 2023-03-28T02:04:40Z\n\nPushed: 2026-02-04T19:00:26Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n[![CircleCI](https://dl.circleci.com/status-badge/img/gh/sambanova/generative_data_prep/tree/main.svg?style=svg)](https://dl.circleci.com/status-badge/redirect/gh/sambanova/generative_data_prep/tree/main)\n[![codecov](https://codecov.io/gh/sambanova/generative_data_prep/graph/badge.svg?token=9CYRCUOOAO)](https://codecov.io/gh/sambanova/generative_data_prep)\n[![Python](https://img.shields.io/badge/python-%3E=3.7-blue.svg)](https://www.python.org/)\n[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)\n[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n[![flake8](https://img.shields.io/badge/pep8-flake8-blue.svg)](https://github.com/PyCQA/flake8)\n[![bandit](https://img.shields.io/badge/security-bandit-yellow.svg)](https://github.com/PyCQA/bandit)\n[![isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)\n[![mypy](https://img.shields.io/badge/mypy-checked-green.svg)](http://mypy-lang.org/)\n\n<a href=\"https://sambanova.ai/\">\n<picture>\n<source media=\"(prefers-color-scheme: dark)\" srcset=\"/img/SambaNova-light-logo-1.png\" height=\"60\">\n<img alt=\"Text changing depending on mode. Light: 'So light!' Dark: 'So dark!'\" src=\"/img/SambaNova-dark-logo-1.png\" height=\"60\">\n</picture>\n</a>\n\n# Generative data preparation\n\nThis software package allows you to prepare datasets for training generative LLMs on SambaStudio and SambaNova's Reconfigurable Data Units (RDUs). Some features include efficient multiprocessing, shuffling data that outsizes RAM, and specifying tokens to attend to during training.\n\nThe [`pipeline.py`](https://github.com/sambanova/generative_data_prep/blob/main/generative_data_prep/data_prep/pipeline.py) script streamlines the data preparation process. It takes a single input file, shuffles and splits it into train/dev/test files, token"},{"ref":"P4","kind":"page","title":"sambanova/bloomchat repository metadata","date":"2026-06-11T04:10:35.13791+00:00","date_source":null,"source_url":"https://github.com/sambanova/bloomchat","signal_url":null,"signal_json_url":null,"text":"# sambanova/bloomchat\n\nDescription: This repo contains the data preparation, tokenization, training and inference code for BLOOMChat. BLOOMChat is a 176 billion parameter multilingual chat model based on BLOOM.\n\nLanguage: Python\n\nLicense: NOASSERTION\n\nStars: 583\n\nForks: 52\n\nOpen issues: 0\n\nCreated: 2023-05-16T22:51:12Z\n\nPushed: 2023-10-10T20:53:21Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n[![CircleCI](https://dl.circleci.com/status-badge/img/gh/sambanova/bloomchat/tree/main.svg?style=svg)](https://dl.circleci.com/status-badge/redirect/gh/sambanova/bloomchat/tree/main)\n[![Python](https://img.shields.io/badge/python-%3E=3.7-blue.svg)](https://www.python.org/)\n[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)\n[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n[![flake8](https://img.shields.io/badge/pep8-flake8-blue.svg)](https://github.com/PyCQA/flake8)\n[![bandit](https://img.shields.io/badge/security-bandit-yellow.svg)](https://github.com/PyCQA/bandit)\n[![isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)\n[![mypy](https://img.shields.io/badge/mypy-checked-green.svg)](http://mypy-lang.org/)\n\n<a href=\"https://sambanova.ai/\">\n<picture>\n<source media=\"(prefers-color-scheme: dark)\" srcset=\"/docs/source/img/SambaNova-light-logo-1.png\" height=\"60\">\n<img alt=\"Text changing depending on mode. Light: 'So light!' Dark: 'So dark!'\" src=\"/docs/source/img/SambaNova-dark-logo-1.png\" height=\"60\">\n</picture>\n</a>\n\n# BLOOMChat Training Repo\n\n## Overview\nThis repo contains the data preparation, tokenization, training and inference code for [BLOOMChat-176B-v1](https://huggingface.co/sambanovasystems/BLOOMChat-176B-v1). BLOOMChat is a 176 billion parameter multilingual chat model. It is instruction tuned from [BLOOM (176B)](https://huggingface.co/bigscience/bloom) on assistant-style conversation datasets and supports conversation, question answering and generative answers in multiple languages.\n\nWe trained BLOOMChat on [SambaNova DataScale systems](htt"},{"ref":"P5","kind":"page","title":"sambanova/tutorials repository metadata","date":"2026-06-11T04:10:34.947806+00:00","date_source":null,"source_url":"https://github.com/sambanova/tutorials","signal_url":null,"signal_json_url":null,"text":"# sambanova/tutorials\n\nLanguage: Jupyter Notebook\n\nLicense: Apache-2.0\n\nStars: 13\n\nForks: 1\n\nOpen issues: 0\n\nCreated: 2023-09-15T19:07:06Z\n\nPushed: 2024-04-30T21:13:28Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n= SambaNova tutorials\n\nThis repository contains SambaNova tutorials that help you to learn more about the SambaNova platform. Each tutorial includes instructions for preparing the dataset, the code to run the model, and pointers to code discussions in our public documentation.\n\nStart with the \"Hello, World\" tutorial, which uses a very simple model and the MNIST dataset. You follow some basic steps to run this ML models on the SambaNova platform.\n\nUse the LeNet tutorial to experience a full ML workflow:\n\n. Compile the model for SambaNova processors (RDU)\n. Train the model using a publicly available dataset\n. Save intermediate checkpoints and continue training from a checkpoint\n. Run inference using one of the checkpoints and generate a predictions file\n. Visualize predictions using Jupyter\n\nGo through the `generative_nlp` tutorial to work with a Hugging Face model in the SambaNova environment. \n\n. Download a GPT-2 model (we've chosen a simple model to speed up compilation and fine tuning).\n. Download and prepare a dataset. \n. Compile the model. \n. Fine tune the compiled model using the labeled dataset. \n. Perform inference with the unlabeled dataset to verify that training worked. \n\n== How to use SambaNova tutorials\n\n. Clone this repository\n+\n[source,console]\n----\n$ git clone https://github.com/sambanova/tutorials.git\n----\n\n. Enter one of the directories, e.g. `hello_world`:\n+\n[source,console]\n----\n$ cd tutorials\n# Start with the 'Hello world'\n$ cd hello_world\n# Or choose the intermediate tutorial that uses LeNet\n$ cd lenet\n----\n\n. Follow the instructions in the README file.\n\n== Feedback\n\nPlease provide your feedback at docs@sambanova.ai."},{"ref":"P6","kind":"page","title":"sambanova/toolbench repository metadata","date":"2026-06-11T04:10:34.907132+00:00","date_source":null,"source_url":"https://github.com/sambanova/toolbench","signal_url":null,"signal_json_url":null,"text":"# sambanova/toolbench\n\nDescription: ToolBench, an evaluation suite for LLM tool manipulation capabilities. \n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 179\n\nForks: 11\n\nOpen issues: 1\n\nCreated: 2023-05-19T16:23:35Z\n\nPushed: 2024-02-28T20:07:35Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<a href=\"https://sambanova.ai/\">\n<picture>\n<source media=\"(prefers-color-scheme: dark)\" srcset=\"/images/SambaNova-light-logo-1.png\" height=\"60\">\n<img alt=\"Text changing depending on mode. Light: 'So light!' Dark: 'So dark!'\" src=\"/images/SambaNova-dark-logo-1.png\" height=\"60\">\n</picture>\n</a>\n\n# ToolBench\n\n<p>\n<a href=\"https://huggingface.co/spaces/qiantong-xu/toolbench-leaderboard\">\n<img src=\"https://img.shields.io/badge/leaderboard-0.0.0-yellow\"\nalt=\"leaderboard\"></a>\n<a href=\"https://discord.gg/JehFG5HXKb\">\n<img src=\"https://img.shields.io/discord/1105549926475247626?logo=discord\"\nalt=\"chat on Discord\"></a>\n</p>\n\n<img src=\"./images/toolbench.jpg\" title=\"SambaNova\" height=\"180\" />\nRecent studies on software tool manipulation with large language models (LLMs) mostly rely on closed model APIs (e.g. OpenAI), as there is an significant gap of model accuracy between those closed models and all the rest open-source LLMs.\nTo study the root cause of the gap and further facilitate the development of open-source LLMs, especially their capabilities on tool manipulation, we create the ToolBench. \nThe ToolBench is a benchmark consisting of diverse software tools for real-world tasks. \nWe also provide easy-to-use infrastructure in this repository to directly evaluate the execution success rate of each model. \nContributions to this repo are highly welcomed! We are excited to see new action generation algorithms and new testing tasks.\n\n## Table of contents\n- [Prerequisites](#prerequisites)\n- [Installation](#installation)\n- [Usage](#usage)\n- [Tasks](#tasks)\n- [Available Checkpoints](#checkpoints)\n\n## Prerequisites \n\n### Credentials\n- Create an [OpenAI account](https://platform.openai.com/account/api-keys) and register an API key.\n- Follow [this guide](https://developers.google.com/workspace/guides/create-credentials#service-account) to create a Google Cloud service account and cre"},{"ref":"P7","kind":"page","title":"sambanova/SN-13B-8k-Instruct repository metadata","date":"2026-06-11T04:10:34.703193+00:00","date_source":null,"source_url":"https://github.com/sambanova/SN-13B-8k-Instruct","signal_url":null,"signal_json_url":null,"text":"# sambanova/SN-13B-8k-Instruct\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 5\n\nForks: 0\n\nOpen issues: 1\n\nCreated: 2023-08-04T00:05:29Z\n\nPushed: 2023-08-07T16:18:11Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# SN-13B-8k-Instruct\n## Basic Information\n- Blog Post: [Link](https://sambanova.ai/blog/training-long-sequence-size-models-on-sambanova/)\n- Discord: [Link](https://discord.gg/8z2Pe7cpRv)\n- SN-13B-8k-Instruct: [Link](https://huggingface.co/sambanovasystems/SN-13B-8k-Instruct)\n\n## Reproducibility Information\nThis repo contains the reproducibility information for the numbers listed in the SN-13B-8k-Instruct blogpost. Scrolls and ZeroScrolls refer to the following benchmarks:\n1. [Scrolls Benchmark](https://www.scrolls-benchmark.com/)\n2. [ZeroScrolls Benchmark](https://www.zero.scrolls-benchmark.com/)\n\n### Setup Eleuther AI LM Evaluation Harness\n1. git clone https://github.com/EleutherAI/lm-evaluation-harness.git\n2. Checkout the commit of LM Evaluation Harness that we used to collect the results:\n```\ngit checkout fe803c2920a85f6afb74ea05d1d2f98ec27f1a63`\n```\n3. Follow the setup instructions specified in the repository's README.\n\n### ZeroScrolls Reproducibility\n1. Add [ZeroScrolls task code](zero_scrolls.py) to the LM Evaluation Harness.\n- This will involve importing the zero scrolls tasks in the `tasks/__init__.py` file in LM Evaluation Harness. You will need to add the following line to the `TASK_REGISTRY`:\n```python\n**zero_scrolls.construct_tasks(),\n```\n2. Install [requirements](requirements.txt)\n```\npip install requirements.txt\n```\n3. Run the following command in the LM Evaluation Harness:\n```\npython main.py --batch_size 1 --tasks zero_scrolls_gov_report,zero_scrolls_summ_screen_fd,zero_scrolls_qm_sum,zero_scrolls_squality,zero_scrolls_qasper,zero_scrolls_narrative_qa,zero_scrolls_quality,zero_scrolls_musique,zero_scrolls_space_digest,zero_scrolls_book_sum_sort --model gpt2 --model_args pretrained=sambanovasystems/SN-13B-8k-Instruct,dtype=float16 --num_fewshot 0 --no_cache\n```\n\n### Scrolls Reproducibility\n1. In the LM Evaluation Harness, open `tasks/scrolls.py` and replace the `'\\n'` with your model's end of text token in the `until` list for all"},{"ref":"P8","kind":"page","title":"sambanova/langchain-sambanova repository metadata","date":"2026-06-11T04:10:34.258111+00:00","date_source":null,"source_url":"https://github.com/sambanova/langchain-sambanova","signal_url":null,"signal_json_url":null,"text":"# sambanova/langchain-sambanova\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 3\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2025-01-10T19:10:30Z\n\nPushed: 2026-02-03T22:09:56Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<a href=\"https://sambanova.ai/\">\n<picture>\n<source media=\"(prefers-color-scheme: dark)\" srcset=\"./img/SambaNova-light-logo-1.png\" height=\"60\">\n<img alt=\"SambaNova logo\" src=\"./img/SambaNova-dark-logo-1.png\" height=\"60\">\n</picture>\n</a>\n\n# langchain-sambanova\n\nThis package contains the LangChain integration with SambaNova\n\n## Installation\n\n```bash\npip install -U langchain-sambanova\n```\n\nAnd you should configure credentials by setting the following environment variables:\n\nIf you are a SambaCloud user:\n\n```bash\nexport SAMBANOVA_API_KEY=\"your-sambacloud-api-key-here\"\n```\n> You can obtain a free SambaCloud API key [here](https://cloud.sambanova.ai/)\n\nIf you are a SambaStack user:\n\n```bash\nexport SAMBANOVA_API_BASE=\"your-sambastack-api-base-url-here\"\nexport SAMBANOVA_API_KEY=\"your-sambastack-api-key-here\"\n```\n\n## Chat Models\n\n### SambaNova\n\n`ChatSambaNova` class exposes chat models from SambaNova unified interface for SambaCloud and SambaStack.\n\n```python\nfrom langchain_sambanova import ChatSambaNova\n\nllm = ChatSambaNova(\nmodel = \"Llama-4-Maverick-17B-128E-Instruct\",\ntemperature = 0.7\n)\nllm.invoke(\"Tell me a joke about artificial intelligence.\")\n```\n\n## Embeddings\n\n### SambaNova\n\n`SambaNovaEmbeddings` class exposes embeddings from SambaNova unified interface for SambaCloud and SambaStack.\n\n```python\nfrom langchain_sambanova import SambaNovaEmbeddings\n\nembeddings = SambaNovaEmbeddings(\nmodel=\"E5-Mistral-7B-Instruct\"\n)\nembeddings.embed_query(\"What is the meaning of life?\")\n```"},{"ref":"P9","kind":"page","title":"sambanova/ai-starter-kit repository metadata","date":"2026-06-11T04:10:34.231061+00:00","date_source":null,"source_url":"https://github.com/sambanova/ai-starter-kit","signal_url":null,"signal_json_url":null,"text":"# sambanova/ai-starter-kit\n\nLanguage: Jupyter Notebook\n\nLicense: NOASSERTION\n\nStars: 249\n\nForks: 80\n\nOpen issues: 24\n\nCreated: 2023-10-06T16:34:46Z\n\nPushed: 2026-06-03T15:51:01Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<a href=\"https://sambanova.ai/\">\n<picture>\n<source media=\"(prefers-color-scheme: dark)\" srcset=\"./images/light-logo.png\" height=\"100\">\n<img alt=\"SambaNova logo\" src=\"./images/dark-logo.png\" height=\"100\">\n</picture>\n</a>\n\n# SambaNova AI Starter Kits\n\n# Overview\n\nSambaNova AI Starter Kits are a collection of open-source examples and guides designed to facilitate the deployment of AI-driven use cases for both developers and enterprises.\n\nTo run these examples, you can obtain a free API key using [SambaCloud](https://cloud.sambanova.ai). Alternatively, if you are a current SambaNova customer, you can deploy your models using [SambaStack](https://sambanova.ai/products/sambastack) or [SambaManaged](https://sambanova.ai/products/sambamanaged). Most of the code examples are written in Python, although the concepts can be applied to any programming language.\n\nQuestions? Just <a href=\"https://community.sambanova.ai/latest\" target=\"_blank\">message us</a> on SambaNova Community <a href=\"https://community.sambanova.ai/latest\" target=\"_blank\"><img src=\"https://github.com/sambanova/ai-starter-kit/assets/150964187/aef53b52-1dc0-4cbf-a3be-55048675f583\" alt=\"Community\" width=\"22\"/></a> or <a href=\"https://github.com/sambanova/ai-starter-kit/issues/new/choose\" target=\"_blank\">create an issue</a> in GitHub. We're happy to help live!\n\n# Available AI Starter Kits\n\nThe table below lists the available kits, which are grouped into four categories: 1) Data Ingestion & Preparation, 2) Model Development & Optimization, 3) Intelligent Information Retrieval, and 4) Advanced AI Capabilities.\n\nFor functionalities related to third-party integrations, find a list in our [Integrations Repository](https://github.com/sambanova/integrations) and [Integrations Docs](https://docs.sambanova.ai/cloud/docs/integrations).\n\n<table style=\"width: 100%;\">\n<thead>\n<tr>\n<th width=\"20%\">Name</th>\n<th width=\"45%\">Kit Description</th>\n<th width=\"15%\">Category</th>\n\n</tr>\n</thead>\n\n<tbo"},{"ref":"P10","kind":"page","title":"sambanova/agents repository metadata","date":"2026-06-11T04:10:33.99037+00:00","date_source":null,"source_url":"https://github.com/sambanova/agents","signal_url":null,"signal_json_url":null,"text":"# sambanova/agents\n\nLanguage: Python\n\nStars: 59\n\nForks: 13\n\nOpen issues: 2\n\nCreated: 2025-01-17T15:30:53Z\n\nPushed: 2026-05-05T21:48:57Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n![Samba Agents Logo](https://sambanova.ai/hs-fs/hubfs/sn-new-gray-logo.png?width=400&height=88&name=sn-new-gray-logo.png)\n\n<h1 style=\"font-size: 3em;\">Agents</h1>\n\nThe Agents application is an advanced multi-agent AI system that intelligently routes requests to specialized agents and subgraphs for comprehensive assistance. The system features a compound agent architecture with XML-based routing, code execution capabilities, and multi-step research workflows. The Agents application helps users by:\n\n- Providing intelligent assistance through a unified compound agent system.\n- Executing code in secure Daytona sandbox environments.\n- Performing comprehensive data science workflows with multi-agent collaboration.\n- Generating detailed research reports and educational content.\n- Conducting advanced financial analysis with real-time data.\n- Automatically routing queries to appropriate specialized subgraphs.\n- Supporting voice input for natural interaction.\n\nThe basic process of the Agents application is described below.\n\n1. **Enhanced agent processing**\n- User submits a query via text or voice input.\n- The compound agent system uses XML-based routing to determine the best approach.\n- Queries are processed through the main agent or routed to specialized subgraphs.\n\n1. **Intelligent subgraph routing**\n- The system automatically determines if queries require specialized subgraph processing.\n- Available subgraphs include: Financial Analysis, Deep Research, Data Science, and Code Execution.\n- Multi-agent collaboration within subgraphs for complex workflows.\n\n1. **Tool and data integration**\n- Dynamic tool loading based on user context and permissions.\n- Integration with external APIs, databases, and knowledge sources.\n- Secure code execution and file generation in Daytona sandbox.\n\n1. **Real-time response generation**\n- WebSocket-based streaming for real-time updates and agent reasoning.\n- Structured responses with metadata for appropriate UI rendering.\n- File artifacts (PDF, HTML, imag"},{"ref":"P11","kind":"page","title":"sambanova/integrations repository metadata","date":"2026-06-11T04:10:33.955618+00:00","date_source":null,"source_url":"https://github.com/sambanova/integrations","signal_url":null,"signal_json_url":null,"text":"# sambanova/integrations\n\nLanguage: Python\n\nStars: 5\n\nForks: 7\n\nOpen issues: 1\n\nCreated: 2025-02-21T23:09:58Z\n\nPushed: 2026-04-10T17:56:42Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<a href=\"https://sambanova.ai/\">\n<picture>\n<source media=\"(prefers-color-scheme: dark)\" srcset=\"./images/SambaNova-light-logo-1.png\" height=\"60\">\n<img alt=\"SambaNova logo\" src=\"./images/SambaNova-dark-logo-1.png\" height=\"60\">\n</picture>\n</a>\n\n# SambaNova Cloud Integrations\n\nWelcome to the SambaNova Cloud API ecosystem, where everyday our fast inference models are expanding alongside the best tools in the developer community. Explore the partners available below and get started building\\! \n\n### Need Assistance? \n\nIf you have any suggestions of integrations or questions, please post on our [Community Page](https://community.sambanova.ai/) so we can follow up. \n\n## Integrations\n\n| Company/Package | Type | Description | Access |\n| :---- | :---- | :---- | :---- |\n| **ADK** | Agent building and orchestration | The Agent Development Kit (ADK) is a modular, model-agnostic framework developed by Google for building AI agents | [Demo code](./adk/README.md) |\n| **Agno** | Agent building and orchestration | Agno is a lightweight framework for building multi-modal AI agents | [Documentation](https://docs.agno.com/models/sambanova) |\n| **AI Suite** | LLM frameworks | AI Suite simplifies access to multiple large language models through a unified interface. | [Documentation](https://docs.sambanova.ai/cloud/docs/integrations/aisuite) |\n| **AutoGen** | Agent building and orchestration | AutoGen is an open-source tool that defines agents, integrates LLMs, and handles task termination. | [Demo code](./autogen/) |\n| **Browser Use** | Tool and Browser Use | Browser Use is an open-source project enabling AI agents to control web browsers, facilitating tasks like automated web navigation and data extraction. | [Documentation](https://docs.browser-use.com/quickstart) |\n| **Camel** | Agent building and orchestration | Camel AI is an open-source framework for intelligent agents, and supports building, customizing, and deploying multi-agent systems. | [Demo code](./camel/) |\n| **Cline** | Coding as"},{"ref":"P12","kind":"page","title":"sambanova/sambanova-ai-provider repository metadata","date":"2026-06-11T04:10:33.954858+00:00","date_source":null,"source_url":"https://github.com/sambanova/sambanova-ai-provider","signal_url":null,"signal_json_url":null,"text":"# sambanova/sambanova-ai-provider\n\nDescription: Vercel AI Provider for running LLMs locally using SambaNova models\n\nLanguage: TypeScript\n\nLicense: Apache-2.0\n\nStars: 4\n\nForks: 2\n\nOpen issues: 1\n\nCreated: 2025-03-20T16:52:46Z\n\nPushed: 2025-10-22T16:34:11Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# sambanova-ai-provider\n\nVercel AI Provider for running LLMs locally using SambaNova's models.\n\n## Table of Contents \n\n- [Requirements](#requirements)\n- [Installation](#installation)\n- [Setup Environment](#setup-environment)\n- [Provider Instance](#provider-instance)\n- [Models](#models)\n- [Tested models and capabilities](#tested-models-and-capabilities)\n- [Image input](#image-input)\n- [Tool calling](#tool-calling)\n- [Embeddings](#embeddings)\n- [Examples](#examples)\n- [Intercepting Fetch requests](#intercepting-fetch-requests)\n\n## Requirements\n\nAPI key can be obtained from the [SambaNova Cloud Platform](https://cloud.sambanova.ai/apis).\n\n## Installation\n\nThe SambaNova provider is available in the `sambanova-ai-provider` module. You can install it with\n\nnpm:\n\n```bash\nnpm install sambanova-ai-provider\n```\n\nyarn:\n\n```bash\nyarn add sambanova-ai-provider\n```\n\nor pnpm:\n\n```bash\npnpm add sambanova-ai-provider\n```\n\n## Setup Environment\n\nYou will need to setup a `SAMBANOVA_API_KEY` environment variable. You can get your API key on the [SambaNova Cloud Portal](https://cloud.sambanova.ai/apis).\n\n## Provider Instance\n\nYou can import the default provider instance `sambanova` from `sambanova-ai-provider`:\n\n```ts\nimport { sambanova } from 'sambanova-ai-provider';\n```\n\nIf you need a customized setup, you can import `createSambaNova` from `sambanova-ai-provider` and create a provider instance with your settings:\n\n```ts\nimport { createSambaNova } from 'sambanova-ai-provider';\n\nconst sambanova = createSambaNova({\napiKey: 'YOUR_API_KEY',\n// Optional settings\n});\n```\n\nYou can use the following optional settings to customize the SambaNova provider instance:\n\n- **baseURL** _string_\n\nUse a different URL prefix for API calls, e.g. to use proxy servers.\nThe default prefix is `https://api.sambanova.ai/v1`.\n\n- **apiKey** _string_\n\nAPI key that is being sent using the `Authorization` head"},{"ref":"P13","kind":"page","title":"sambanova/n8n-nodes-sambanova repository metadata","date":"2026-06-11T04:10:33.475097+00:00","date_source":null,"source_url":"https://github.com/sambanova/n8n-nodes-sambanova","signal_url":null,"signal_json_url":null,"text":"# sambanova/n8n-nodes-sambanova\n\nLanguage: JavaScript\n\nLicense: MIT\n\nStars: 0\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2025-06-18T20:14:36Z\n\nPushed: 2025-07-11T16:18:13Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# n8n-nodes-sambanova\n\nThis is an n8n community node. It lets you use **SambaNova Language Models** in your n8n workflows.\n\nSambaNova provides advanced AI language models for natural language understanding and generation, enabling you to integrate state-of-the-art AI capabilities into your automation workflows.\n\n[n8n](https://n8n.io/) is a [fair-code licensed](https://docs.n8n.io/reference/license/) workflow automation platform.\n\n[Installation](#installation) \n[Operations](#operations) \n[Credentials](#credentials) \n[Compatibility](#compatibility) \n[Usage](#usage) \n[Resources](#resources) \n[Version history](#version-history) \n\n## Installation\n\nFollow the [installation guide](https://docs.n8n.io/integrations/community-nodes/installation/) in the n8n community nodes documentation.\n\n## Operations\n\n- Connect to SambaNova's API to select and run language models.\n- Fetch available models dynamically.\n- Configure token limits and temperature for completions.\n- Output a language model object to be used in AI chains or agents.\n\n## Credentials\n\nYou need to provide an API key from SambaNova to use this node.\n\n1. Sign up or log in to [SambaNova Cloud](https://cloud.sambanova.ai/?utm_source=continue&utm_medium=external&utm_campaign=cloud_signup).\n2. Obtain your API key from the SambaNova dashboard.\n3. In n8n, create new credentials of type **SambaNova**.\n4. Enter your API key into the credentials form.\n\n## Compatibility\n\n- Minimum n8n version: 1.98.1 \n- Tested on: n8n version 1.101.1\n- Requires Node.js version >=20.15\n\n## Usage\n\n- Add the **SambaNova Chat Model** node to your workflow.\n- Select your desired language model.\n- Adjust options such as maximum tokens and temperature.\n- Connect this node's output to AI chains or other compatible nodes.\n\nIf you're new to n8n, check out the [Try it out](https://docs.n8n.io/try-it-out/) guide to get started.\n\n## Resources\n\n* [n8n community nodes documentation](https://docs.n8n.io/integrations/#community-nodes)\n* [Samba"},{"ref":"P14","kind":"page","title":"sambanova/tokenizers repository metadata","date":"2026-06-11T04:10:33.304384+00:00","date_source":null,"source_url":"https://github.com/sambanova/tokenizers","signal_url":null,"signal_json_url":null,"text":"# sambanova/tokenizers\n\nStars: 0\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2025-06-24T19:56:26Z\n\nPushed: 2025-07-03T21:06:50Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Tokenizers\n\nThis repo contains pre-loaded tokenizers files from Hugging Face for the following models:\n\n- Meta-Llama-3-8B (with extended vocab)\n- Meta-Llama-3-8B-Instruct (with extended vocab)\n- Meta-Llama-3.1-8B\n- Meta-Llama-3.1-8B-Instruct\n- Meta-Llama-3.1-70B\n- Meta-Llama-3.1-70B-Instruct\n- Meta-Llama-3.2-1B\n- Meta-Llama-3.2-1B-Instruct \n- Meta-Llama-3.2-3B\n- Meta-Llama-3.2-3B-Instruct\n- Mistral-7B-v0.3:\n- Mistral-7B-Instruct-v0.3\n- GPT2"},{"ref":"P15","kind":"page","title":"sambanova/sambanova-python repository metadata","date":"2026-06-11T04:10:33.196665+00:00","date_source":null,"source_url":"https://github.com/sambanova/sambanova-python","signal_url":null,"signal_json_url":null,"text":"# sambanova/sambanova-python\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 2\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2025-08-20T22:16:11Z\n\nPushed: 2026-05-26T21:57:51Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Samba Nova Python API library\n\n<!-- prettier-ignore -->\n[![PyPI version](https://img.shields.io/pypi/v/sambanova.svg?label=pypi%20(stable))](https://pypi.org/project/sambanova/)\n\nThe Samba Nova Python library provides convenient access to the Samba Nova REST API from any Python 3.9+\napplication. The library includes type definitions for all request params and response fields,\nand offers both synchronous and asynchronous clients powered by [httpx](https://github.com/encode/httpx).\n\nIt is generated with [Stainless](https://www.stainless.com/).\n\n## Documentation\n\nThe REST API documentation can be found on [docs.sambanova.ai](https://docs.sambanova.ai). The full API of this library can be found in [api.md](api.md).\n\n## Installation\n\n```sh\n# install from PyPI\npip install sambanova\n```\n\n## Usage\n\nThe full API of this library can be found in [api.md](api.md).\n\n```python\nimport os\nfrom sambanova import SambaNova\n\nclient = SambaNova(\napi_key=os.environ.get(\"SAMBANOVA_API_KEY\"), # This is the default and can be omitted\n)\n\ncompletion = client.chat.completions.create(\nmessages=[\n{\n\"content\": \"create a poem using palindromes\",\n\"role\": \"user\",\n}\n],\nmodel=\"gpt-oss-120b\",\n)\n```\n\n## Responses API\n\n```python\nimport os\nfrom sambanova import SambaNova\n\nclient = SambaNova(\napi_key=os.environ.get(\"SAMBANOVA_API_KEY\"),\n)\n\nresponse = client.responses.create(\nmodel=\"gpt-oss-120b\",\ninput=\"Explain disestablishmentarianism to a smart five year old.\",\n)\nprint(response.output_text)\n```\n\nWhile you can provide an `api_key` keyword argument,\nwe recommend using [python-dotenv](https://pypi.org/project/python-dotenv/)\nto add `SAMBANOVA_API_KEY=\"My API Key\"` to your `.env` file\nso that your API Key is not stored in source control.\n\n## Async usage\n\nSimply import `AsyncSambaNova` instead of `SambaNova` and use `await` with each API call:\n\n```python\nimport os\nimport asyncio\nfrom sambanova import AsyncSambaNova\n\nclient = AsyncSambaNova(\napi_key=os.environ.get(\"SAMBANOVA_API_KEY\"), # "},{"ref":"P16","kind":"page","title":"sambanova/sambanova-typescript repository metadata","date":"2026-06-11T04:10:33.162301+00:00","date_source":null,"source_url":"https://github.com/sambanova/sambanova-typescript","signal_url":null,"signal_json_url":null,"text":"# sambanova/sambanova-typescript\n\nLanguage: TypeScript\n\nLicense: Apache-2.0\n\nStars: 1\n\nForks: 1\n\nOpen issues: 0\n\nCreated: 2025-08-20T22:17:13Z\n\nPushed: 2026-05-26T21:58:28Z\n\nDefault branch: next\n\nFork: no\n\nArchived: no\n\nREADME:\n# Samba Nova TypeScript API Library\n\n[![NPM version](<https://img.shields.io/npm/v/sambanova.svg?label=npm%20(stable)>)](https://npmjs.org/package/sambanova) ![npm bundle size](https://img.shields.io/bundlephobia/minzip/sambanova)\n\nThis library provides convenient access to the Samba Nova REST API from server-side TypeScript or JavaScript.\n\nThe REST API documentation can be found on [docs.sambanova.ai](https://docs.sambanova.ai). The full API of this library can be found in [api.md](api.md).\n\nIt is generated with [Stainless](https://www.stainless.com/).\n\n## Installation\n\n```sh\nnpm install sambanova\n```\n\n## Usage\n\nThe full API of this library can be found in [api.md](api.md).\n\n<!-- prettier-ignore -->\n```js\nimport SambaNova from 'sambanova';\n\nconst client = new SambaNova({\napiKey: process.env['SAMBANOVA_API_KEY'], // This is the default and can be omitted\n});\n\nconst completion = await client.chat.completions.create({\nmessages: [{ content: 'create a poem using palindromes', role: 'user' }],\nmodel: 'gpt-oss-120b',\n});\n```\n\n## Responses API\n\n<!-- prettier-ignore -->\n```js\nimport SambaNova from 'sambanova';\n\nconst client = new SambaNova({\napiKey: process.env['SAMBANOVA_API_KEY'],\n});\n\nconst response = await client.responses.create({\nmodel: 'gpt-oss-120b',\ninput: 'Explain disestablishmentarianism to a smart five year old.',\n});\nconsole.log(response.output_text);\n```\n\n## Streaming responses\n\nWe provide support for streaming responses using Server Sent Events (SSE).\n\n```ts\nimport SambaNova from 'sambanova';\n\nconst client = new SambaNova();\n\nconst stream = await client.chat.completions.create({\nmessages: [{ content: 'create a poem using palindromes', role: 'user' }],\nmodel: 'gpt-oss-120b',\nstream: true,\n});\nfor await (const chatCompletionStreamResponse of stream) {\nconsole.log(chatCompletionStreamResponse);\n}\n```\n\nIf you need to cancel a stream, you can `break` from the loop\nor call `stream.controller.abort()`.\n\n### Request & Response types\n\nThis "},{"ref":"P17","kind":"page","title":"sambanova/sambanova-ai-provider v1.2.0","date":"2026-06-11T04:06:14.842909+00:00","date_source":null,"source_url":"https://github.com/sambanova/sambanova-ai-provider/releases/tag/v1.2.0","signal_url":null,"signal_json_url":null,"text":"# v1.2.0\n\nRepository: sambanova/sambanova-ai-provider\n\nTag: v1.2.0\n\nPublished: 2025-08-28T18:54:23Z\n\nPrerelease: no\n\nRelease notes:\n### Minor Changes\n\n- Updated aisk version"},{"ref":"P18","kind":"page","title":"sambanova/sambanova-ai-provider v1.1.2","date":"2026-06-11T04:06:14.477632+00:00","date_source":null,"source_url":"https://github.com/sambanova/sambanova-ai-provider/releases/tag/v1.1.2","signal_url":null,"signal_json_url":null,"text":"# v1.1.2\n\nRepository: sambanova/sambanova-ai-provider\n\nTag: v1.1.2\n\nPublished: 2025-04-15T15:37:44Z\n\nPrerelease: no\n\nRelease notes:\n### Patch Changes\n\n- Remove deprecated models\n- Update vite version"},{"ref":"P19","kind":"page","title":"sambanova/langchain-sambanova v0.1.5","date":"2026-06-11T04:06:14.446271+00:00","date_source":null,"source_url":"https://github.com/sambanova/langchain-sambanova/releases/tag/v0.1.5","signal_url":null,"signal_json_url":null,"text":"# v0.1.5\n\nRepository: sambanova/langchain-sambanova\n\nTag: v0.1.5\n\nPublished: 2025-05-06T17:54:09Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* Feat: enable json schema structured output by @snova-jorgep in https://github.com/sambanova/langchain-sambanova/pull/20\n\n**Full Changelog**: https://github.com/sambanova/langchain-sambanova/compare/v0.1.4...v0.1.5"},{"ref":"P20","kind":"page","title":"sambanova/sambanova-ai-provider v1.1.3","date":"2026-06-11T04:06:14.414383+00:00","date_source":null,"source_url":"https://github.com/sambanova/sambanova-ai-provider/releases/tag/v1.1.3","signal_url":null,"signal_json_url":null,"text":"# v1.1.3\n\nRepository: sambanova/sambanova-ai-provider\n\nTag: v1.1.3\n\nPublished: 2025-04-16T21:18:49Z\n\nPrerelease: no\n\nRelease notes:\n### Patch Changes\n\n- Adding Llama 4 models for multimodal"},{"ref":"P21","kind":"page","title":"sambanova/langchain-sambanova v0.1.6","date":"2026-06-11T04:06:14.306492+00:00","date_source":null,"source_url":"https://github.com/sambanova/langchain-sambanova/releases/tag/v0.1.6","signal_url":null,"signal_json_url":null,"text":"# v0.1.6\n\nRepository: sambanova/langchain-sambanova\n\nTag: v0.1.6\n\nPublished: 2025-07-08T13:25:45Z\n\nPrerelease: no\n\nRelease notes: none published."},{"ref":"P22","kind":"page","title":"sambanova/langchain-sambanova v0.2.0","date":"2026-06-11T04:06:14.00339+00:00","date_source":null,"source_url":"https://github.com/sambanova/langchain-sambanova/releases/tag/v0.2.0","signal_url":null,"signal_json_url":null,"text":"# v0.2.0\n\nRepository: sambanova/langchain-sambanova\n\nTag: v0.2.0\n\nPublished: 2025-10-07T17:55:23Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* Feat: SambaNovaChat and SambaNovaEmbeddings from SambaNova official SDK by @snova-jorgep in https://github.com/sambanova/langchain-sambanova/pull/24\n\n**Full Changelog**: https://github.com/sambanova/langchain-sambanova/compare/v0.1.6...v0.2.0"},{"ref":"P23","kind":"page","title":"sambanova/sambanova-ai-provider v1.2.1","date":"2026-06-11T04:06:13.986508+00:00","date_source":null,"source_url":"https://github.com/sambanova/sambanova-ai-provider/releases/tag/v1.2.1","signal_url":null,"signal_json_url":null,"text":"# v1.2.1\n\nRepository: sambanova/sambanova-ai-provider\n\nTag: v1.2.1\n\nPublished: 2025-09-17T18:48:12Z\n\nPrerelease: no\n\nRelease notes:\n### Patch Changes\n\n- Model list updates"},{"ref":"P24","kind":"page","title":"sambanova/ai-starter-kit aisk_with_old_kits","date":"2026-06-11T04:06:13.936353+00:00","date_source":null,"source_url":"https://github.com/sambanova/ai-starter-kit/releases/tag/aisk_with_old_kits","signal_url":null,"signal_json_url":null,"text":"# aisk_with_old_kits\n\nRepository: sambanova/ai-starter-kit\n\nTag: aisk_with_old_kits\n\nPublished: 2025-10-14T17:42:53Z\n\nPrerelease: no\n\nRelease notes:\nThis is the AI Starter Kit available until Oct 14, 2025 using the old SambaNova Cloud and SambaStudio LangChain wrappers. The available kits are: benchmarking, bundle_jump_start, data_extraction, document_comparison, e2e_fine_tuning, EKR, eval_jumpstart, financial_assistant, fine_tuning_embeddings, fine_tuning_sql, function_calling, google_integration, image_search, multimodal knowledge retriever, PCA, prompt_engineering, quickstart, sambanova_scribe, search_assistant, web_crawled_data_retriever, and utils."},{"ref":"P25","kind":"page","title":"sambanova/langchain-sambanova v1.0.0","date":"2026-06-11T04:06:13.810733+00:00","date_source":null,"source_url":"https://github.com/sambanova/langchain-sambanova/releases/tag/v1.0.0","signal_url":null,"signal_json_url":null,"text":"# v1.0.0\n\nRepository: sambanova/langchain-sambanova\n\nTag: v1.0.0\n\nPublished: 2025-10-22T16:28:28Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* Chore update 1.0.0 by @snova-luiss in https://github.com/sambanova/langchain-sambanova/pull/25\n\n**Full Changelog**: https://github.com/sambanova/langchain-sambanova/compare/v0.2.0...v1.0.0"},{"ref":"P26","kind":"page","title":"sambanova/sambanova-ai-provider v1.2.2","date":"2026-06-11T04:06:13.70004+00:00","date_source":null,"source_url":"https://github.com/sambanova/sambanova-ai-provider/releases/tag/v1.2.2","signal_url":null,"signal_json_url":null,"text":"# v1.2.2\n\nRepository: sambanova/sambanova-ai-provider\n\nTag: v1.2.2\n\nPublished: 2025-10-22T16:34:12Z\n\nPrerelease: no\n\nRelease notes:\n### Patch Changes\n\n- Adding structured outputs option"},{"ref":"P27","kind":"page","title":"sambanova/sambanova-python v1.7.0","date":"2026-06-11T04:06:13.560659+00:00","date_source":null,"source_url":"https://github.com/sambanova/sambanova-python/releases/tag/v1.7.0","signal_url":null,"signal_json_url":null,"text":"# v1.7.0\n\nRepository: sambanova/sambanova-python\n\nTag: v1.7.0\n\nPublished: 2026-04-21T19:34:29Z\n\nPrerelease: no\n\nRelease notes:\n## 1.7.0 (2026-04-21)\n\nFull Changelog: [v1.6.1...v1.7.0](https://github.com/sambanova/sambanova-python/compare/v1.6.1...v1.7.0)\n\n### Features\n\n* **api:** add n and seed chat completions parameters ([bf3c1b5](https://github.com/sambanova/sambanova-python/commit/bf3c1b54d9c2c5db97358de25e72b81542a6fa9f))\n* **api:** Responses API Support ([76c215b](https://github.com/sambanova/sambanova-python/commit/76c215ba649a76be104e466e6ea1b202a89ebf61))\n\n### Bug Fixes\n\n* **client:** preserve hardcoded query params when merging with user params ([b29dd32](https://github.com/sambanova/sambanova-python/commit/b29dd3268636349e0e40c618d3003739d2a070dc))\n* ensure file data are only sent as 1 parameter ([74ba3cc](https://github.com/sambanova/sambanova-python/commit/74ba3cc25421e62f3e5b1087ddeef431355b410e))\n\n### Performance Improvements\n\n* **client:** optimize file structure copying in multipart requests ([31410a1](https://github.com/sambanova/sambanova-python/commit/31410a1f9f3b40894d87f3b70cebf1774d50b629))\n\n### Chores\n\n* **tests:** bump steady to v0.22.1 ([68deab8](https://github.com/sambanova/sambanova-python/commit/68deab8cb895253503eb21ae492ac913260a9264))\n\n### Documentation\n\n* improve examples ([06546f4](https://github.com/sambanova/sambanova-python/commit/06546f41c4658591980f6f466488df2ff0f5e6be))\n* update examples ([a21f0fb](https://github.com/sambanova/sambanova-python/commit/a21f0fb6358a4665536ddf9b25e9c9ff81073b80))"},{"ref":"P28","kind":"page","title":"sambanova/langchain-sambanova v1.1.0","date":"2026-06-11T04:06:13.548186+00:00","date_source":null,"source_url":"https://github.com/sambanova/langchain-sambanova/releases/tag/v1.1.0","signal_url":null,"signal_json_url":null,"text":"# v1.1.0\n\nRepository: sambanova/langchain-sambanova\n\nTag: v1.1.0\n\nPublished: 2026-02-03T22:09:56Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n\n* feat: add integration_source parameter for SDK analytics\n\n* ci: add Python 3.13 to test matrix\n\n* fix: update serialization tests for langchain-core 1.2+ security restrictions\n\n* Fix: Handle AIMessage content_blocks format in message conversion\n\n* Docs add comprehensive usage guide notebook\n\nby @snova-jorgep in https://github.com/sambanova/langchain-sambanova/pull/26\n\n**Full Changelog**: https://github.com/sambanova/langchain-sambanova/compare/v1.0.0...v1.1.0"},{"ref":"E1","kind":"event","title":"Gemma 4 31B Runs Fastest on SambaCloud","date":"2026-06-10T19:25:29+00:00","date_source":"rss.item_date","source_url":"https://sambanova.ai/blog/gemma-4-31b-running-fastest-on-sambacloud","signal_url":"https://onlylabs.fyi/signals/0d69079d-f097-4af0-8bee-276617f9ed74","signal_json_url":"https://onlylabs.fyi/signals/0d69079d-f097-4af0-8bee-276617f9ed74/signal.json","text":"post_published · Gemma 4 31B Runs Fastest on SambaCloud · signal_desk=talking · occurred_at=2026-06-10T19:25:29+00:00 · url=https://sambanova.ai/blog/gemma-4-31b-running-fastest-on-sambacloud · raw={\"excerpt\":\"Gemma 4 31B is Google DeepMind's most capable dense open model to date — and it's running fastest on SambaCloud. Try it today for reasoning, coding, and agentic workflows on SambaCloud.\"}"},{"ref":"E2","kind":"event","title":"Full Stack Support  Engineer","date":"2026-06-05T20:47:04+00:00","date_source":"source","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5921351004","signal_url":"https://onlylabs.fyi/signals/3c08b871-c3c0-4c57-9631-66a1d50d1d00","signal_json_url":"https://onlylabs.fyi/signals/3c08b871-c3c0-4c57-9631-66a1d50d1d00/signal.json","text":"job_opened · Full Stack Support  Engineer · signal_desk=hiring · occurred_at=2026-06-05T20:47:04+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5921351004 · raw={\"location\":\"Remote - US\",\"ats\":\"greenhouse\"}"},{"ref":"E3","kind":"event","title":"Senior Software Engineer, ML Infrastructure","date":"2026-06-05T18:55:39+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=6007942004","signal_url":"https://onlylabs.fyi/signals/3a4b09c1-7250-4521-a628-be52de6b39e1","signal_json_url":"https://onlylabs.fyi/signals/3a4b09c1-7250-4521-a628-be52de6b39e1/signal.json","text":"job_opened · Senior Software Engineer, ML Infrastructure · signal_desk=hiring · occurred_at=2026-06-05T18:55:39+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=6007942004 · raw={\"location\":\"Remote - US\",\"ats\":\"greenhouse\"}"},{"ref":"E4","kind":"event","title":"Technical Program Manager, Software Engineering","date":"2026-06-05T17:35:46+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5817488004","signal_url":"https://onlylabs.fyi/signals/038c49c3-ae26-48f9-908f-38a7c5ef8ef7","signal_json_url":"https://onlylabs.fyi/signals/038c49c3-ae26-48f9-908f-38a7c5ef8ef7/signal.json","text":"job_opened · Technical Program Manager, Software Engineering · signal_desk=hiring · occurred_at=2026-06-05T17:35:46+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5817488004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E5","kind":"event","title":"Supply Chain Specialist","date":"2026-06-04T23:40:50+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=6013330004","signal_url":"https://onlylabs.fyi/signals/1976b2a9-6fcd-47dd-8bfd-5aeaa66db543","signal_json_url":"https://onlylabs.fyi/signals/1976b2a9-6fcd-47dd-8bfd-5aeaa66db543/signal.json","text":"job_opened · Supply Chain Specialist · signal_desk=hiring · occurred_at=2026-06-04T23:40:50+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=6013330004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E6","kind":"event","title":"ML Features Solutions Engineer","date":"2026-06-04T22:12:54+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5819022004","signal_url":"https://onlylabs.fyi/signals/4ee95568-c5c4-4b23-be79-b4fefe1ecf4c","signal_json_url":"https://onlylabs.fyi/signals/4ee95568-c5c4-4b23-be79-b4fefe1ecf4c/signal.json","text":"job_opened · ML Features Solutions Engineer · signal_desk=hiring · occurred_at=2026-06-04T22:12:54+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5819022004 · raw={\"location\":\"Austin, Texas, United States; San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E7","kind":"event","title":"Principal Compiler Engineer - ML Systems","date":"2026-06-04T22:11:54+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5719056004","signal_url":"https://onlylabs.fyi/signals/2e58cf68-8fc8-4e34-a7c9-4d7b78451eb0","signal_json_url":"https://onlylabs.fyi/signals/2e58cf68-8fc8-4e34-a7c9-4d7b78451eb0/signal.json","text":"job_opened · Principal Compiler Engineer - ML Systems · signal_desk=hiring · occurred_at=2026-06-04T22:11:54+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5719056004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E8","kind":"event","title":"Senior Cloud Platform Engineer","date":"2026-06-04T22:10:17+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5719049004","signal_url":"https://onlylabs.fyi/signals/3ff730ff-d5f7-46b8-b9d9-9e8b60903f1e","signal_json_url":"https://onlylabs.fyi/signals/3ff730ff-d5f7-46b8-b9d9-9e8b60903f1e/signal.json","text":"job_opened · Senior Cloud Platform Engineer · signal_desk=hiring · occurred_at=2026-06-04T22:10:17+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5719049004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E9","kind":"event","title":"Software Engineer, ML Inference Performance","date":"2026-06-04T20:47:21+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5742971004","signal_url":"https://onlylabs.fyi/signals/52526f59-ef17-4cef-8ab0-2de1815b03c9","signal_json_url":"https://onlylabs.fyi/signals/52526f59-ef17-4cef-8ab0-2de1815b03c9/signal.json","text":"job_opened · Software Engineer, ML Inference Performance · signal_desk=hiring · occurred_at=2026-06-04T20:47:21+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5742971004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E10","kind":"event","title":"Cloud Site Reliability Engineer","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5983754004","signal_url":"https://onlylabs.fyi/signals/a4f63f2b-a971-4c21-8884-91e116c82510","signal_json_url":"https://onlylabs.fyi/signals/a4f63f2b-a971-4c21-8884-91e116c82510/signal.json","text":"job_opened · Cloud Site Reliability Engineer · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5983754004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E11","kind":"event","title":"Manufacturing Testing Engineer","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5831918004","signal_url":"https://onlylabs.fyi/signals/f47c9704-7bba-46fd-b03a-fa4f32727d66","signal_json_url":"https://onlylabs.fyi/signals/f47c9704-7bba-46fd-b03a-fa4f32727d66/signal.json","text":"job_opened · Manufacturing Testing Engineer · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5831918004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E12","kind":"event","title":"Software Engineer","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5817837004","signal_url":"https://onlylabs.fyi/signals/3588e3e9-f384-4537-9ede-0e8768fc9eb2","signal_json_url":"https://onlylabs.fyi/signals/3588e3e9-f384-4537-9ede-0e8768fc9eb2/signal.json","text":"job_opened · Software Engineer · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5817837004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E13","kind":"event","title":"Sr Product Manager - AI Cloud","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5811778004","signal_url":"https://onlylabs.fyi/signals/cb13d12c-9136-4f0b-8e11-c74b6448ae07","signal_json_url":"https://onlylabs.fyi/signals/cb13d12c-9136-4f0b-8e11-c74b6448ae07/signal.json","text":"job_opened · Sr Product Manager - AI Cloud · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5811778004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E14","kind":"event","title":"Software Architect","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=6012016004","signal_url":"https://onlylabs.fyi/signals/af367686-2dfb-4ed7-8ec3-f591b9f78801","signal_json_url":"https://onlylabs.fyi/signals/af367686-2dfb-4ed7-8ec3-f591b9f78801/signal.json","text":"job_opened · Software Architect · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=6012016004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E15","kind":"event","title":"Principal Engineer, High-Speed IO & Memory Systems","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5869372004","signal_url":"https://onlylabs.fyi/signals/97468d4f-5b4d-48b1-86fc-3a85d49b3e73","signal_json_url":"https://onlylabs.fyi/signals/97468d4f-5b4d-48b1-86fc-3a85d49b3e73/signal.json","text":"job_opened · Principal Engineer, High-Speed IO & Memory Systems · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5869372004 · raw={\"location\":\"Austin, Texas, United States; San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E16","kind":"event","title":"Director, Software Engineering","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=6011958004","signal_url":"https://onlylabs.fyi/signals/8407614c-f984-48d8-b8a0-187bdb627d16","signal_json_url":"https://onlylabs.fyi/signals/8407614c-f984-48d8-b8a0-187bdb627d16/signal.json","text":"job_opened · Director, Software Engineering · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=6011958004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E17","kind":"event","title":"Senior Technical Program Manager","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5813960004","signal_url":"https://onlylabs.fyi/signals/824c5cbd-af99-44c5-b1e2-a1089acb9d7f","signal_json_url":"https://onlylabs.fyi/signals/824c5cbd-af99-44c5-b1e2-a1089acb9d7f/signal.json","text":"job_opened · Senior Technical Program Manager · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5813960004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E18","kind":"event","title":"Senior Software Engineer - Kernel & Device Drivers ","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5850439004","signal_url":"https://onlylabs.fyi/signals/247a82c4-7387-4f0a-8201-93243730e4de","signal_json_url":"https://onlylabs.fyi/signals/247a82c4-7387-4f0a-8201-93243730e4de/signal.json","text":"job_opened · Senior Software Engineer - Kernel & Device Drivers  · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5850439004 · raw={\"location\":\"Austin, Texas, United States; San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E19","kind":"event","title":"Senior Hardware Validation & SI Correlation Engineer","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5850481004","signal_url":"https://onlylabs.fyi/signals/d6474c22-ef30-4e52-ac3b-c521b6d7ae54","signal_json_url":"https://onlylabs.fyi/signals/d6474c22-ef30-4e52-ac3b-c521b6d7ae54/signal.json","text":"job_opened · Senior Hardware Validation & SI Correlation Engineer · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5850481004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E20","kind":"event","title":"Senior AI Systems Performance Engineer","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5719052004","signal_url":"https://onlylabs.fyi/signals/488a3e37-8c54-46c1-9a44-90a3cece481b","signal_json_url":"https://onlylabs.fyi/signals/488a3e37-8c54-46c1-9a44-90a3cece481b/signal.json","text":"job_opened · Senior AI Systems Performance Engineer · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5719052004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E21","kind":"event","title":"Runtime Engineer ","date":"2026-06-04T17:23:25+00:00","date_source":"greenhouse.updated_at","source_url":"https://sambanova.ai/sambanova-available-positions/?gh_jid=5835758004","signal_url":"https://onlylabs.fyi/signals/5553a00a-9afc-4186-854b-bb275d7a572a","signal_json_url":"https://onlylabs.fyi/signals/5553a00a-9afc-4186-854b-bb275d7a572a/signal.json","text":"job_opened · Runtime Engineer  · signal_desk=hiring · occurred_at=2026-06-04T17:23:25+00:00 · url=https://sambanova.ai/sambanova-available-positions/?gh_jid=5835758004 · raw={\"location\":\"San Jose, California, United States\",\"ats\":\"greenhouse\"}"},{"ref":"E22","kind":"event","title":"The First Disaggregated Inference Demo for AI Agents Is Live","date":"2026-06-03T12:27:26+00:00","date_source":"rss.item_date","source_url":"https://sambanova.ai/blog/first-disaggregated-inference-demo-for-ai-agents-live","signal_url":"https://onlylabs.fyi/signals/e0ffb630-93c9-4da6-a877-68d76d422ef3","signal_json_url":"https://onlylabs.fyi/signals/e0ffb630-93c9-4da6-a877-68d76d422ef3/signal.json","text":"post_published · The First Disaggregated Inference Demo for AI Agents Is Live · signal_desk=talking · occurred_at=2026-06-03T12:27:26+00:00 · url=https://sambanova.ai/blog/first-disaggregated-inference-demo-for-ai-agents-live · raw={\"excerpt\":\"TL;DR\\n \\r\\n \\r\\n \\nSambaNova demonstrated live disaggregated inference at COMPUTEX using Nvidia B200 for prefill and SN40 RDU for decode.\\n \\r\\n \\nSpeed is 2x faster than B200-only configurations, verified by Artificial Analysis.\\n \\r\\n \\nThe architecture is live at Vector Core Compute's (VC2) data center.\\n \\r\\n \\nTogether.ai is the first commercial customer.\\n \\r\\n \\nSN50, targeting 10x throughput at 500 tokens per second per user on MiniMax M2.7, is expected in the second half of the year.\\n \\r\\n \\r\\nSambaNova demonstrates how GPUs and RDUs work together to deliver premium inference for agent workloads using the right chip for the right workload.\\n \\r\\nAt COMPUTEX, SambaNova demonstrated what the next era of AI inference looks like: Premium inference for AI agents powered by GPUs and RDUs, running live in the newly-announced VC2 data center for the first time.\\n \\r\\nUsing Nvidia’s B200 GPU for prefill and SambaNova’s SN40 RDU for decode, the inference speed generated is 2X the speed of B200-only configurations, as verified by Artificial Intelligence. \\n \\r\\nThis is running today out of Vector Core Compute's (VC2) data center, with Together.AI as the first commercial customer to use the inference capabilities from VC2.\"}"},{"ref":"E23","kind":"event","title":"sambanova/sambanova-typescript v1.7.0","date":"2026-05-26T21:58:03+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-typescript/releases/tag/v1.7.0","signal_url":"https://onlylabs.fyi/signals/2531dac0-42e0-41f4-afd8-f8f65a550eb3","signal_json_url":"https://onlylabs.fyi/signals/2531dac0-42e0-41f4-afd8-f8f65a550eb3/signal.json","text":"release · sambanova/sambanova-typescript v1.7.0 · signal_desk=releases · occurred_at=2026-05-26T21:58:03+00:00 · url=https://github.com/sambanova/sambanova-typescript/releases/tag/v1.7.0 · raw={\"repo\":\"sambanova/sambanova-typescript\"}"},{"ref":"E24","kind":"event","title":"sambanova/sambanova-python v1.9.0","date":"2026-05-26T21:57:32+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-python/releases/tag/v1.9.0","signal_url":"https://onlylabs.fyi/signals/dd7cded0-7acf-4acc-8ca6-d43e0e448b2d","signal_json_url":"https://onlylabs.fyi/signals/dd7cded0-7acf-4acc-8ca6-d43e0e448b2d/signal.json","text":"release · sambanova/sambanova-python v1.9.0 · signal_desk=releases · occurred_at=2026-05-26T21:57:32+00:00 · url=https://github.com/sambanova/sambanova-python/releases/tag/v1.9.0 · raw={\"repo\":\"sambanova/sambanova-python\"}"},{"ref":"E25","kind":"event","title":"Build Faster Coding Agents with SambaNova’s Responses API","date":"2026-05-11T18:49:08+00:00","date_source":"rss.item_date","source_url":"https://sambanova.ai/blog/build-faster-coding-agents-with-sambanovas-responses-api","signal_url":"https://onlylabs.fyi/signals/d3e11495-4da9-46b7-b3ff-2a8dc9cb73ea","signal_json_url":"https://onlylabs.fyi/signals/d3e11495-4da9-46b7-b3ff-2a8dc9cb73ea/signal.json","text":"post_published · Build Faster Coding Agents with SambaNova’s Responses API · signal_desk=talking · occurred_at=2026-05-11T18:49:08+00:00 · url=https://sambanova.ai/blog/build-faster-coding-agents-with-sambanovas-responses-api · raw={\"excerpt\":\"SambaNova is launching support for the Responses API across the SambaNova platform — SambaCloud, SambaStack, and SambaManaged — giving AI engineers a cleaner way to connect modern coding agents to fast, production-ready models. /v1/responses support starts with gpt-oss-120b, MiniMax M2.5, and MiniMax M2.7.\"}"},{"ref":"E26","kind":"event","title":"sambanova/sambanova-typescript v1.6.2","date":"2026-05-07T14:50:43+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-typescript/releases/tag/v1.6.2","signal_url":"https://onlylabs.fyi/signals/5bd43464-9b05-4b91-b420-f262c4939c40","signal_json_url":"https://onlylabs.fyi/signals/5bd43464-9b05-4b91-b420-f262c4939c40/signal.json","text":"release · sambanova/sambanova-typescript v1.6.2 · signal_desk=releases · occurred_at=2026-05-07T14:50:43+00:00 · url=https://github.com/sambanova/sambanova-typescript/releases/tag/v1.6.2 · raw={\"repo\":\"sambanova/sambanova-typescript\"}"},{"ref":"E27","kind":"event","title":"sambanova/sambanova-python v1.8.2","date":"2026-05-07T14:48:58+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-python/releases/tag/v1.8.2","signal_url":"https://onlylabs.fyi/signals/bac49e55-493e-4221-8310-00397563240e","signal_json_url":"https://onlylabs.fyi/signals/bac49e55-493e-4221-8310-00397563240e/signal.json","text":"release · sambanova/sambanova-python v1.8.2 · signal_desk=releases · occurred_at=2026-05-07T14:48:58+00:00 · url=https://github.com/sambanova/sambanova-python/releases/tag/v1.8.2 · raw={\"repo\":\"sambanova/sambanova-python\"}"},{"ref":"E28","kind":"event","title":"sambanova/sambanova-python v1.8.1","date":"2026-05-05T22:13:18+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-python/releases/tag/v1.8.1","signal_url":"https://onlylabs.fyi/signals/6ddec0d9-d5b1-4ed5-b21e-a4214fedcf2b","signal_json_url":"https://onlylabs.fyi/signals/6ddec0d9-d5b1-4ed5-b21e-a4214fedcf2b/signal.json","text":"release · sambanova/sambanova-python v1.8.1 · signal_desk=releases · occurred_at=2026-05-05T22:13:18+00:00 · url=https://github.com/sambanova/sambanova-python/releases/tag/v1.8.1 · raw={\"repo\":\"sambanova/sambanova-python\"}"},{"ref":"E29","kind":"event","title":"sambanova/sambanova-typescript v1.6.1","date":"2026-05-05T22:12:57+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-typescript/releases/tag/v1.6.1","signal_url":"https://onlylabs.fyi/signals/f2b2b753-0f42-41d9-a88b-4b05415a6c7b","signal_json_url":"https://onlylabs.fyi/signals/f2b2b753-0f42-41d9-a88b-4b05415a6c7b/signal.json","text":"release · sambanova/sambanova-typescript v1.6.1 · signal_desk=releases · occurred_at=2026-05-05T22:12:57+00:00 · url=https://github.com/sambanova/sambanova-typescript/releases/tag/v1.6.1 · raw={\"repo\":\"sambanova/sambanova-typescript\"}"},{"ref":"E30","kind":"event","title":"sambanova/sambanova-typescript v1.6.0","date":"2026-05-05T21:51:49+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-typescript/releases/tag/v1.6.0","signal_url":"https://onlylabs.fyi/signals/a8731478-89cb-4308-8eda-a0fcd1657915","signal_json_url":"https://onlylabs.fyi/signals/a8731478-89cb-4308-8eda-a0fcd1657915/signal.json","text":"release · sambanova/sambanova-typescript v1.6.0 · signal_desk=releases · occurred_at=2026-05-05T21:51:49+00:00 · url=https://github.com/sambanova/sambanova-typescript/releases/tag/v1.6.0 · raw={\"repo\":\"sambanova/sambanova-typescript\"}"},{"ref":"E31","kind":"event","title":"sambanova/sambanova-python v1.8.0","date":"2026-05-05T21:50:03+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-python/releases/tag/v1.8.0","signal_url":"https://onlylabs.fyi/signals/a2c0f1ec-0b40-4e67-b066-365720eccfcf","signal_json_url":"https://onlylabs.fyi/signals/a2c0f1ec-0b40-4e67-b066-365720eccfcf/signal.json","text":"release · sambanova/sambanova-python v1.8.0 · signal_desk=releases · occurred_at=2026-05-05T21:50:03+00:00 · url=https://github.com/sambanova/sambanova-python/releases/tag/v1.8.0 · raw={\"repo\":\"sambanova/sambanova-python\"}"},{"ref":"E32","kind":"event","title":"MiniMax M2.7 Running Fastest on SambaCloud","date":"2026-05-05T15:30:11+00:00","date_source":"rss.item_date","source_url":"https://sambanova.ai/blog/build-self-evolving-agents-on-sambacloud-with-minimax-2.7","signal_url":"https://onlylabs.fyi/signals/aca77565-bb67-40c7-ac92-9e307d5cd846","signal_json_url":"https://onlylabs.fyi/signals/aca77565-bb67-40c7-ac92-9e307d5cd846/signal.json","text":"post_published · MiniMax M2.7 Running Fastest on SambaCloud · signal_desk=talking · occurred_at=2026-05-05T15:30:11+00:00 · url=https://sambanova.ai/blog/build-self-evolving-agents-on-sambacloud-with-minimax-2.7 · raw={\"excerpt\":\"Build Self-Evolving Agents, Use it for Coding or OpenClaw\\n \\r\\nMiniMax M2.7 (M2.7) is the latest frontier model from MiniMax — and it’s running fastest on SambaCloud. Try it today for coding and OpenClaw on SambaCloud.\\n \\r\\nTL;DR: MiniMax M2.7\\n \\r\\n \\r\\n \\nMiniMax M2.7 is an open-weight frontier model built for coding and multi-agent workflows\\n \\r\\n \\nRuns fastest on SambaCloud, available on Developer and Enterprise tiers\\n \\r\\n \\nTop coding benchmarks: 56.22% SWE-Pro, 76.5% SWE Multilingual, 66.6% medal rate on MLE Bench Lite\\n \\r\\n \\nRanks alongside Claude Opus 4.6 and GPT-5.4 on agentic tasks at a fraction of the cost\\n \\r\\n \\nNatively supports multi-agent frameworks including OpenClaw and CrewAI\\n \\r\\n \\nAccessible via SambaCloud playground or API with the model name MiniMax M2.7\"}"},{"ref":"E33","kind":"event","title":"Many-Shot Prompting: A Practical Guide to In-Context Learning at Scale","date":"2026-04-22T21:12:20+00:00","date_source":"rss.item_date","source_url":"https://sambanova.ai/blog/many-shot-prompting-a-practical-guide-to-icl","signal_url":"https://onlylabs.fyi/signals/3572e310-653a-450c-909b-aaf3eb82c076","signal_json_url":"https://onlylabs.fyi/signals/3572e310-653a-450c-909b-aaf3eb82c076/signal.json","text":"post_published · Many-Shot Prompting: A Practical Guide to In-Context Learning at Scale · signal_desk=talking · occurred_at=2026-04-22T21:12:20+00:00 · url=https://sambanova.ai/blog/many-shot-prompting-a-practical-guide-to-icl · raw={\"excerpt\":\"TL;DR: What We Found\\n \\r\\nWe ran thousands of experiments on many-shot in-context learning (ICL) across multiple benchmarks, model sizes, and prompting strategies. Here are the headline findings:\"}"},{"ref":"E34","kind":"event","title":"sambanova/sambanova-typescript v1.5.0","date":"2026-04-21T19:35:51+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-typescript/releases/tag/v1.5.0","signal_url":"https://onlylabs.fyi/signals/6505802d-dbf3-4c36-97e3-df097941db4e","signal_json_url":"https://onlylabs.fyi/signals/6505802d-dbf3-4c36-97e3-df097941db4e/signal.json","text":"release · sambanova/sambanova-typescript v1.5.0 · signal_desk=releases · occurred_at=2026-04-21T19:35:51+00:00 · url=https://github.com/sambanova/sambanova-typescript/releases/tag/v1.5.0 · raw={\"repo\":\"sambanova/sambanova-typescript\"}"},{"ref":"E35","kind":"event","title":"sambanova/sambanova-python v1.7.0","date":"2026-04-21T19:34:29+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-python/releases/tag/v1.7.0","signal_url":"https://onlylabs.fyi/signals/74ba1029-3441-4487-9796-2d590a71c2be","signal_json_url":"https://onlylabs.fyi/signals/74ba1029-3441-4487-9796-2d590a71c2be/signal.json","text":"release · sambanova/sambanova-python v1.7.0 · signal_desk=releases · occurred_at=2026-04-21T19:34:29+00:00 · url=https://github.com/sambanova/sambanova-python/releases/tag/v1.7.0 · raw={\"repo\":\"sambanova/sambanova-python\"}"},{"ref":"E36","kind":"event","title":"Dataflow Architecture for AI Inference Explained | SambaNova","date":"2026-04-16T15:50:57+00:00","date_source":"rss.item_date","source_url":"https://sambanova.ai/blog/why-dataflow-matters-more-than-ever","signal_url":"https://onlylabs.fyi/signals/0fd1d594-0b43-42c5-ad62-c793619194c2","signal_json_url":"https://onlylabs.fyi/signals/0fd1d594-0b43-42c5-ad62-c793619194c2/signal.json","text":"post_published · Dataflow Architecture for AI Inference Explained | SambaNova · signal_desk=talking · occurred_at=2026-04-16T15:50:57+00:00 · url=https://sambanova.ai/blog/why-dataflow-matters-more-than-ever · raw={\"excerpt\":\"\"}"},{"ref":"E37","kind":"event","title":"Building the Blueprint for Premium Inference","date":"2026-04-08T18:21:14+00:00","date_source":"rss.item_date","source_url":"https://sambanova.ai/blog/sambanova-and-intel-blog","signal_url":"https://onlylabs.fyi/signals/98ba579f-4f65-4bb4-b48e-2ef045fdca84","signal_json_url":"https://onlylabs.fyi/signals/98ba579f-4f65-4bb4-b48e-2ef045fdca84/signal.json","text":"post_published · Building the Blueprint for Premium Inference · signal_desk=talking · occurred_at=2026-04-08T18:21:14+00:00 · url=https://sambanova.ai/blog/sambanova-and-intel-blog · raw={\"excerpt\":\"Premium inference is designed to solve the real problem that agents run into at scale. Agentic systems do not answer one prompt and stop. They reason, call tools, query databases, compile code, invoke sandboxes, validate results, and return to inference again and again until the work is done.\"}"},{"ref":"E38","kind":"event","title":"What is AI Inference? | SambaNova","date":"2026-04-07T07:00:00+00:00","date_source":"rss.item_date","source_url":"https://sambanova.ai/blog/what-is-ai-inference","signal_url":"https://onlylabs.fyi/signals/24b1d7ab-1f70-4788-9cd7-e4e0ce4a66fc","signal_json_url":"https://onlylabs.fyi/signals/24b1d7ab-1f70-4788-9cd7-e4e0ce4a66fc/signal.json","text":"post_published · What is AI Inference? | SambaNova · signal_desk=talking · occurred_at=2026-04-07T07:00:00+00:00 · url=https://sambanova.ai/blog/what-is-ai-inference · raw={\"excerpt\":\"The word “inference,” in English, means a conclusion drawn through reasoning and evidence. Similarly, AI inference relates to an AI model’s ability to infer, or extrapolate, conclusions in new situations, using information gained from training, response, and the fine tuning process. In short, AI inference is the process of using AI models to generate predictions or outputs from new data.\"}"},{"ref":"E39","kind":"event","title":"sambanova/sambanova-plugin-cc","date":"2026-03-31T17:38:58+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-plugin-cc","signal_url":"https://onlylabs.fyi/signals/93001bee-6577-419c-b4d6-f05a9a791774","signal_json_url":"https://onlylabs.fyi/signals/93001bee-6577-419c-b4d6-f05a9a791774/signal.json","text":"repo_new · sambanova/sambanova-plugin-cc · signal_desk=repos · occurred_at=2026-03-31T17:38:58+00:00 · url=https://github.com/sambanova/sambanova-plugin-cc · stars=1 · raw={\"repo\":\"sambanova/sambanova-plugin-cc\",\"language\":\"Python\"}"},{"ref":"E40","kind":"event","title":"Solving the Decode Bottleneck: Why Agentic Inference Needs Hybrid Hardware","date":"2026-03-31T17:00:38+00:00","date_source":"rss.item_date","source_url":"https://sambanova.ai/blog/agentic-inference-needs-hybrid-hardware","signal_url":"https://onlylabs.fyi/signals/53ad089d-560c-4aa8-b9a2-b6a9eabc55b0","signal_json_url":"https://onlylabs.fyi/signals/53ad089d-560c-4aa8-b9a2-b6a9eabc55b0/signal.json","text":"post_published · Solving the Decode Bottleneck: Why Agentic Inference Needs Hybrid Hardware · signal_desk=talking · occurred_at=2026-03-31T17:00:38+00:00 · url=https://sambanova.ai/blog/agentic-inference-needs-hybrid-hardware · raw={\"excerpt\":\"Every day, the AI ecosystem is evolving and pushing for further optimizations from chips to models. Why? Because coding and enterprise agents are delivering real productivity gains to people today in tools like OpenClaw, but they are taking hours – sometimes days – to complete due to the size of these models and the long reasoning chains required to deliver accurate results.\"}"},{"ref":"E41","kind":"event","title":"sambanova/toolbench","date":"2023-05-19T16:23:35+00:00","date_source":"source","source_url":"https://github.com/sambanova/toolbench","signal_url":"https://onlylabs.fyi/signals/047cc867-6f77-46ef-b9df-c1a1ce40c027","signal_json_url":"https://onlylabs.fyi/signals/047cc867-6f77-46ef-b9df-c1a1ce40c027/signal.json","text":"repo_new · sambanova/toolbench · signal_desk=repos · occurred_at=2023-05-19T16:23:35+00:00 · url=https://github.com/sambanova/toolbench · stars=179 · hn=1 points/1 comments · raw={\"repo\":\"sambanova/toolbench\",\"description\":\"ToolBench, an evaluation suite for LLM tool manipulation capabilities. \",\"language\":\"Python\"}"},{"ref":"E42","kind":"event","title":"sambanova/bloomchat","date":"2023-05-16T22:51:12+00:00","date_source":"source","source_url":"https://github.com/sambanova/bloomchat","signal_url":"https://onlylabs.fyi/signals/0915c910-c266-464b-83cf-057911ba2b56","signal_json_url":"https://onlylabs.fyi/signals/0915c910-c266-464b-83cf-057911ba2b56/signal.json","text":"repo_new · sambanova/bloomchat · signal_desk=repos · occurred_at=2023-05-16T22:51:12+00:00 · url=https://github.com/sambanova/bloomchat · stars=583 · raw={\"repo\":\"sambanova/bloomchat\",\"description\":\"This repo contains the data preparation, tokenization, training and inference code for BLOOMChat. BLOOMChat is a 176 billion parameter multilingual chat model based on BLOOM.\",\"language\":\"Python\"}"},{"ref":"E43","kind":"event","title":"sambanova/ai-starter-kit","date":"2023-10-06T16:34:46+00:00","date_source":"source","source_url":"https://github.com/sambanova/ai-starter-kit","signal_url":"https://onlylabs.fyi/signals/a0aec18f-ced7-48ec-908f-b58aa4814692","signal_json_url":"https://onlylabs.fyi/signals/a0aec18f-ced7-48ec-908f-b58aa4814692/signal.json","text":"repo_new · sambanova/ai-starter-kit · signal_desk=repos · occurred_at=2023-10-06T16:34:46+00:00 · url=https://github.com/sambanova/ai-starter-kit · stars=249 · raw={\"repo\":\"sambanova/ai-starter-kit\",\"language\":\"Jupyter Notebook\"}"},{"ref":"E44","kind":"event","title":"sambanova/generative_data_prep","date":"2023-03-28T02:04:40+00:00","date_source":"source","source_url":"https://github.com/sambanova/generative_data_prep","signal_url":"https://onlylabs.fyi/signals/82c927c1-c6f1-45de-b7e6-d49c493b7256","signal_json_url":"https://onlylabs.fyi/signals/82c927c1-c6f1-45de-b7e6-d49c493b7256/signal.json","text":"repo_new · sambanova/generative_data_prep · signal_desk=repos · occurred_at=2023-03-28T02:04:40+00:00 · url=https://github.com/sambanova/generative_data_prep · stars=67 · raw={\"repo\":\"sambanova/generative_data_prep\",\"language\":\"Python\"}"},{"ref":"E45","kind":"event","title":"sambanova/agents","date":"2025-01-17T15:30:53+00:00","date_source":"source","source_url":"https://github.com/sambanova/agents","signal_url":"https://onlylabs.fyi/signals/2aaf684e-d309-4f05-914d-2dcaec13a619","signal_json_url":"https://onlylabs.fyi/signals/2aaf684e-d309-4f05-914d-2dcaec13a619/signal.json","text":"repo_new · sambanova/agents · signal_desk=repos · occurred_at=2025-01-17T15:30:53+00:00 · url=https://github.com/sambanova/agents · stars=59 · raw={\"repo\":\"sambanova/agents\",\"language\":\"Python\"}"},{"ref":"E46","kind":"event","title":"sambanova/tutorials","date":"2023-09-15T19:07:06+00:00","date_source":"source","source_url":"https://github.com/sambanova/tutorials","signal_url":"https://onlylabs.fyi/signals/888311a9-2009-447f-848a-75f3d89a24da","signal_json_url":"https://onlylabs.fyi/signals/888311a9-2009-447f-848a-75f3d89a24da/signal.json","text":"repo_new · sambanova/tutorials · signal_desk=repos · occurred_at=2023-09-15T19:07:06+00:00 · url=https://github.com/sambanova/tutorials · stars=13 · raw={\"repo\":\"sambanova/tutorials\",\"language\":\"Jupyter Notebook\"}"},{"ref":"E47","kind":"event","title":"sambanova/integrations","date":"2025-02-21T23:09:58+00:00","date_source":"source","source_url":"https://github.com/sambanova/integrations","signal_url":"https://onlylabs.fyi/signals/87c9fd25-ab4a-4680-ad9d-6399f265a155","signal_json_url":"https://onlylabs.fyi/signals/87c9fd25-ab4a-4680-ad9d-6399f265a155/signal.json","text":"repo_new · sambanova/integrations · signal_desk=repos · occurred_at=2025-02-21T23:09:58+00:00 · url=https://github.com/sambanova/integrations · stars=5 · raw={\"repo\":\"sambanova/integrations\",\"language\":\"Python\"}"},{"ref":"E48","kind":"event","title":"sambanova/SN-13B-8k-Instruct","date":"2023-08-04T00:05:29+00:00","date_source":"source","source_url":"https://github.com/sambanova/SN-13B-8k-Instruct","signal_url":"https://onlylabs.fyi/signals/7f12b0f3-251c-4d6c-bfb4-12f7327ee1ff","signal_json_url":"https://onlylabs.fyi/signals/7f12b0f3-251c-4d6c-bfb4-12f7327ee1ff/signal.json","text":"repo_new · sambanova/SN-13B-8k-Instruct · signal_desk=repos · occurred_at=2023-08-04T00:05:29+00:00 · url=https://github.com/sambanova/SN-13B-8k-Instruct · stars=5 · raw={\"repo\":\"sambanova/SN-13B-8k-Instruct\",\"language\":\"Python\"}"},{"ref":"E49","kind":"event","title":"sambanova/sambanova-ai-provider","date":"2025-03-20T16:52:46+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-ai-provider","signal_url":"https://onlylabs.fyi/signals/2026a79a-f29d-4b25-8397-2401b2463b1e","signal_json_url":"https://onlylabs.fyi/signals/2026a79a-f29d-4b25-8397-2401b2463b1e/signal.json","text":"repo_new · sambanova/sambanova-ai-provider · signal_desk=repos · occurred_at=2025-03-20T16:52:46+00:00 · url=https://github.com/sambanova/sambanova-ai-provider · stars=4 · raw={\"repo\":\"sambanova/sambanova-ai-provider\",\"description\":\"Vercel AI Provider for running LLMs locally using SambaNova models\",\"language\":\"TypeScript\"}"},{"ref":"E50","kind":"event","title":"sambanova/langchain-sambanova","date":"2025-01-10T19:10:30+00:00","date_source":"source","source_url":"https://github.com/sambanova/langchain-sambanova","signal_url":"https://onlylabs.fyi/signals/7448ddd3-c21d-412b-b2c0-dff5e3b366fe","signal_json_url":"https://onlylabs.fyi/signals/7448ddd3-c21d-412b-b2c0-dff5e3b366fe/signal.json","text":"repo_new · sambanova/langchain-sambanova · signal_desk=repos · occurred_at=2025-01-10T19:10:30+00:00 · url=https://github.com/sambanova/langchain-sambanova · stars=3 · raw={\"repo\":\"sambanova/langchain-sambanova\",\"language\":\"Python\"}"},{"ref":"E51","kind":"event","title":"sambanova/lm-evaluation-harness","date":"2024-03-08T16:10:36+00:00","date_source":"source","source_url":"https://github.com/sambanova/lm-evaluation-harness","signal_url":"https://onlylabs.fyi/signals/6e9f1339-cb77-47c4-8165-d2d1a578c232","signal_json_url":"https://onlylabs.fyi/signals/6e9f1339-cb77-47c4-8165-d2d1a578c232/signal.json","text":"repo_forked · sambanova/lm-evaluation-harness · signal_desk=forks · occurred_at=2024-03-08T16:10:36+00:00 · url=https://github.com/sambanova/lm-evaluation-harness · stars=3 · raw={\"repo\":\"sambanova/lm-evaluation-harness\",\"parent\":\"EleutherAI/lm-evaluation-harness\"}"},{"ref":"E52","kind":"event","title":"sambanova/sambastack-tools","date":"2026-01-15T17:22:22+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambastack-tools","signal_url":"https://onlylabs.fyi/signals/6f5c40bb-23c0-4fb3-b969-cd366373999b","signal_json_url":"https://onlylabs.fyi/signals/6f5c40bb-23c0-4fb3-b969-cd366373999b/signal.json","text":"repo_new · sambanova/sambastack-tools · signal_desk=repos · occurred_at=2026-01-15T17:22:22+00:00 · url=https://github.com/sambanova/sambastack-tools · stars=2 · raw={\"repo\":\"sambanova/sambastack-tools\",\"language\":\"TypeScript\"}"},{"ref":"E53","kind":"event","title":"sambanova/sambanova-python","date":"2025-08-20T22:16:11+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-python","signal_url":"https://onlylabs.fyi/signals/689d13f9-2225-4cae-b806-ef04ae3036e3","signal_json_url":"https://onlylabs.fyi/signals/689d13f9-2225-4cae-b806-ef04ae3036e3/signal.json","text":"repo_new · sambanova/sambanova-python · signal_desk=repos · occurred_at=2025-08-20T22:16:11+00:00 · url=https://github.com/sambanova/sambanova-python · stars=2 · raw={\"repo\":\"sambanova/sambanova-python\",\"language\":\"Python\"}"},{"ref":"E54","kind":"event","title":"sambanova/sambanova-typescript","date":"2025-08-20T22:17:13+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-typescript","signal_url":"https://onlylabs.fyi/signals/6dda1c8d-3d77-4018-815e-fa01a06c0fd8","signal_json_url":"https://onlylabs.fyi/signals/6dda1c8d-3d77-4018-815e-fa01a06c0fd8/signal.json","text":"repo_new · sambanova/sambanova-typescript · signal_desk=repos · occurred_at=2025-08-20T22:17:13+00:00 · url=https://github.com/sambanova/sambanova-typescript · stars=1 · raw={\"repo\":\"sambanova/sambanova-typescript\",\"language\":\"TypeScript\"}"},{"ref":"E55","kind":"event","title":"The AI Efficiency Survey","date":"2026-03-01T00:00:00.000Z","date_source":"page.visible_date","source_url":"https://sambanova.ai/blog/ai-efficiency-survey","signal_url":"https://onlylabs.fyi/signals/bcbee8e1-c209-4de0-8c09-2b65eac8c1b1","signal_json_url":"https://onlylabs.fyi/signals/bcbee8e1-c209-4de0-8c09-2b65eac8c1b1/signal.json","text":"post_published · The AI Efficiency Survey · signal_desk=talking · occurred_at=2026-03-01T00:00:00.000Z · url=https://sambanova.ai/blog/ai-efficiency-survey · raw={\"excerpt\":\"SambaNova commissioned a survey in December 2025 that polled over 2,500 adults across the US and the UK, exploring how people feel about AI’s impact on energy use, electricity costs, and national control of AI infrastructure.\"}"},{"ref":"E56","kind":"event","title":"The OpenClaw x SambaNova Playbook for Agentic Workflows","date":"2026-02-26T23:07:43+00:00","date_source":"source","source_url":"https://sambanova.ai/blog/the-openclaw-x-sambanova-playbook-for-agentic-workflows","signal_url":"https://onlylabs.fyi/signals/299a4396-c696-407a-9b1a-5653cce8d371","signal_json_url":"https://onlylabs.fyi/signals/299a4396-c696-407a-9b1a-5653cce8d371/signal.json","text":"post_published · The OpenClaw x SambaNova Playbook for Agentic Workflows · signal_desk=talking · occurred_at=2026-02-26T23:07:43+00:00 · url=https://sambanova.ai/blog/the-openclaw-x-sambanova-playbook-for-agentic-workflows · raw={\"excerpt\":\"Unless you’ve been sleeping in a cave, you’ve probably heard the buzz about OpenClaw. And if you’ve been scrolling Moltbook at all, you’ve definitely seen it.\"}"},{"ref":"E57","kind":"event","title":"sambanova/langchain-sambanova v1.1.0","date":"2026-02-03T22:09:56+00:00","date_source":"source","source_url":"https://github.com/sambanova/langchain-sambanova/releases/tag/v1.1.0","signal_url":"https://onlylabs.fyi/signals/06d6a96b-8fd8-4695-9670-5793474e6751","signal_json_url":"https://onlylabs.fyi/signals/06d6a96b-8fd8-4695-9670-5793474e6751/signal.json","text":"release · sambanova/langchain-sambanova v1.1.0 · signal_desk=releases · occurred_at=2026-02-03T22:09:56+00:00 · url=https://github.com/sambanova/langchain-sambanova/releases/tag/v1.1.0 · raw={\"repo\":\"sambanova/langchain-sambanova\"}"},{"ref":"E58","kind":"event","title":"sambanova/sambastack-version","date":"2025-12-31T05:55:13+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambastack-version","signal_url":"https://onlylabs.fyi/signals/9e12de07-6b5a-44b3-ab49-b0c337bd3cbe","signal_json_url":"https://onlylabs.fyi/signals/9e12de07-6b5a-44b3-ab49-b0c337bd3cbe/signal.json","text":"repo_new · sambanova/sambastack-version · signal_desk=repos · occurred_at=2025-12-31T05:55:13+00:00 · url=https://github.com/sambanova/sambastack-version · raw={\"repo\":\"sambanova/sambastack-version\",\"description\":\"Version number for SambaStack Helm Charts\"}"},{"ref":"E59","kind":"event","title":"sambanova/sambanova-ai-provider v1.2.2","date":"2025-10-22T16:34:12+00:00","date_source":"source","source_url":"https://github.com/sambanova/sambanova-ai-provider/releases/tag/v1.2.2","signal_url":"https://onlylabs.fyi/signals/9f0622fa-3ce6-4ba6-ab2a-5033e8ebdf1b","signal_json_url":"https://onlylabs.fyi/signals/9f0622fa-3ce6-4ba6-ab2a-5033e8ebdf1b/signal.json","text":"release · sambanova/sambanova-ai-provider v1.2.2 · signal_desk=releases · occurred_at=2025-10-22T16:34:12+00:00 · url=https://github.com/sambanova/sambanova-ai-provider/releases/tag/v1.2.2 · raw={\"repo\":\"sambanova/sambanova-ai-provider\"}"},{"ref":"E60","kind":"event","title":"sambanova/transformers","date":"2024-04-03T20:27:54+00:00","date_source":"source","source_url":"https://github.com/sambanova/transformers","signal_url":"https://onlylabs.fyi/signals/37bad421-a19e-42d9-ad71-4a1765adea87","signal_json_url":"https://onlylabs.fyi/signals/37bad421-a19e-42d9-ad71-4a1765adea87/signal.json","text":"repo_forked · sambanova/transformers · signal_desk=forks · occurred_at=2024-04-03T20:27:54+00:00 · url=https://github.com/sambanova/transformers · raw={\"repo\":\"sambanova/transformers\",\"parent\":\"huggingface/transformers\"}"}]}