{"schema_version":"onlylabs.public_analysis_evidence.v1","title":"MiniMax 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/analysis/minimax","json_url":"https://onlylabs.fyi/analysis/minimax/evidence.json","generated_at":"2026-06-11T18:16:20.105Z","org":{"slug":"minimax","name":"MiniMax","category":"frontier-lab","category_label":"Frontier lab","dossier_url":"https://onlylabs.fyi/labs/minimax"},"analysis":{"url":"https://onlylabs.fyi/analysis/minimax","json_url":"https://onlylabs.fyi/analysis/minimax/analysis.json","generated_at":"2026-06-08T15:59:09.182+00:00"},"workflow":{"version":"synthesize-analyses","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":59,"web":0,"evidence":87,"signal_desks":{"hiring":10,"forks":1,"releases":22,"talking":0,"repos":26},"data_radar_lanes":{"data":1,"evals":0,"infrastructure":2,"safety":0,"product":3},"data_radar_matches":6,"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":"MiniMax-AI/MiniMax-01 repository metadata","date":"2026-06-11T03:57:43.044959+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/MiniMax-01","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/MiniMax-01\n\nDescription: The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 3428\n\nForks: 329\n\nOpen issues: 8\n\nCreated: 2025-01-14T15:43:28Z\n\nPushed: 2025-07-07T12:24:30Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n
Explore these applications integrating MiniMax's multimodal API to see how text, vision, and speech processing capabilities are incorporated into various software. Head to the MiniMax Open Platform to get your API key.
Alipay is a platform for payments and digital services in China. It enables Chinese users to transact globally and allows foreign visitors to link credit cards for widespread acceptance within China. The platform integrates secure, diverse functionalities, streamlining financial interactions and daily services for its users.
\n\n\n\n# One RL to See Them All\nWe propose **V-Triune** (**V**isual **Tri**ple **U**nified Rei**n**forcement L**e**arning), a unified Reinforcement Learning (RL) system designed to advance Vision-Language Models (VLMs). It enables VLMs to jointly learn"},{"ref":"P8","kind":"page","title":"MiniMax-AI/SynLogic repository metadata","date":"2026-06-11T03:57:41.848423+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/SynLogic","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/SynLogic\n\nDescription: [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 203\n\nForks: 22\n\nOpen issues: 1\n\nCreated: 2025-05-23T14:54:08Z\n\nPushed: 2025-07-07T06:03:03Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n
\n\n\n\n# SynLogic\n\nThis repository contains the code and data for SynLogic, a comprehensive logical reasoning data synthesis framework that generates diverse, verifiable reasoning data at scale. Our work addresses the critical gap in high-quality logical reasoning training data for developing general reasoning capabilities in Large Language Models (LLMs).\n\n
\n\n
\n\n## News\n- **[2025/07/07]** :fire: We provide guidance for using SynLogic data to conduct RL training with the Verl framework. See [docs/training_guidance.md](docs/training_guidance.md) for details. \n\n- **[2025/06/03]** :fire: Trained Models Released on Hugging Face: \n→ [MiniMaxAI/SynLogic Collection](https://huggin"},{"ref":"P9","kind":"page","title":"MiniMax-AI/MiniMax-M1 repository metadata","date":"2026-06-11T03:57:41.725058+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/MiniMax-M1","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/MiniMax-M1\n\nDescription: MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 3154\n\nForks: 284\n\nOpen issues: 28\n\nCreated: 2025-06-14T08:54:06Z\n\nPushed: 2025-07-07T11:57:22Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n
\n\n# Meet MiniMax-M2\n\nToday, we release and open source MiniMax-M2, a **Mini** model built for **Max** coding & agentic workflows.\n\n**MiniMax-M2** redefines efficiency for agents. It's a "},{"ref":"P12","kind":"page","title":"MiniMax-AI/minimax_search repository metadata","date":"2026-06-11T03:57:41.076965+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/minimax_search","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/minimax_search\n\nDescription: MiniMax Search is an MCP (Model Context Protocol) server that provides web search and browsing capabilities.\n\nLanguage: Python\n\nStars: 56\n\nForks: 12\n\nOpen issues: 3\n\nCreated: 2025-10-30T14:13:01Z\n\nPushed: 2025-11-03T09:04:57Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# MiniMax Search MCP Server\n\n[English Doc](./README.md) | [Chinese Doc](./README_zh.md)\n\nMiniMax Search is an MCP (Model Context Protocol) server that provides web search and browsing capabilities.\n\n## 🔧 Version Notes\n\nThis project uses the **standard MCP Server protocol**, compliant with MCP specifications:\n- ✅ Complete `list_tools()` implementation\n- ✅ Complete `call_tool()` implementation \n- ✅ Standard `stdio_server()` communication\n\n## Features\n\n- 🔍 **Multi-Engine Search**: Supports Google search engine\n- 🚀 **Parallel Search**: Native support for parallel multi-query search\n- 🌐 **Batch Browsing**: Support for batch browsing of multiple URLs\n- 🤖 **Intelligent Understanding**: Uses MiniMax LLM to understand web content and answer questions\n- 🎯 **Advanced Search**: Supports Google advanced search syntax\n- 🔄 **Auto Fallback**: Automatically switches to other engines when search fails\n\n## Quick Start\n\n### Install via Git (Recommended)\n\n```bash\n# Run directly from Git repository\nuvx --from git+ssh://git@github.com:MiniMax-AI/minimax_search.git minimax-search \n```\n\n### Install via Local Path (Development)\n\n```bash\n# Run from local directory\nuvx --from /xxx/minimax_search minimax-search\n```\n\n### MCP Client Configuration\n\nAdd to your MCP client configuration file (e.g., `mcp.json`):\n\n```json\n{\n\"mcpServers\": {\n\"minimax_search\": {\n\"command\": \"uvx\",\n\"args\": [\n\"--from\",\n\"git+ssh://git@github.com:MiniMax-AI/minimax_search.git\",\n\"minimax-search\"\n],\n\"env\": {\n\"MINIMAX_API_KEY\": \"your_minimax_api_key\",\n\"SERPER_API_KEY\": \"your_serper_api_key\",\n\"JINA_API_KEY\": \"your_jina_api_key\"\n}\n}\n}\n}\n```\n\n## Available Tools\n\n### 1. search - Parallel Web Search\n\nSearch multiple queries simultaneously, returning brief results (title, URL, snippet).\n\n**Parameters**:\n- `queries` (array of strings, required): List of queries, supports Google advanced search syntax\n\n**Supp"},{"ref":"P13","kind":"page","title":"MiniMax-AI/MiniMax-Provider-Verifier repository metadata","date":"2026-06-11T03:57:40.751122+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/MiniMax-Provider-Verifier","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/MiniMax-Provider-Verifier\n\nDescription: MiniMax-Provider-Verifier offers a rigorous, vendor-agnostic way to verify whether third-party deployments of the Minimax M2 model are correct and reliable.\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 46\n\nForks: 9\n\nOpen issues: 1\n\nCreated: 2025-11-10T09:07:34Z\n\nPushed: 2026-06-06T12:59:58Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# MiniMax-Provider-Verifier\n\n[English](README.md) | [中文](README_CN.md)\n\n**MiniMax-Provider-Verifier** offers a rigorous, vendor-agnostic way to verify whether third-party deployments of the Minimax M2 model are correct and reliable. Since the open-source release of M2, it has been widely adopted and integrated into production services by numerous users. To ensure this vast user base continues to benefit from an efficient, high-quality M2 experience—and to align with our vision of \"Intelligence with Everyone\"—this toolkit offers an objective, reproducible standard for validating model behavior.\n\n## Evaluation Metrics\n\nWe evaluate multiple dimensions of vendor deployments, including tool-calling behavior, schema correctness, and system stability (e.g., detecting potential misconfigurations like incorrect top-k settings).\n\nThe primary metrics are:\n\n* **Query-Success-Rate:** Measures the probability that a provider can eventually return a valid response successfully when allowed up to `max_retry=10` attempts.\n- `query_success_rate = successful_query_count / total_query_count`\n\n* **ToolCalls-Match-Rate:** Measures how well the model's \"whether to trigger tool-calls\" behavior matches the expected labels. Each test case is annotated with `expected_tool_call` (whether a tool call is expected), and this metric calculates the proportion of cases where the actual result matches the expected result.\n- `tool_calls_match_rate = (tool_calls_finish_tool_calls + stop_finish_stop) / expected_tool_call_total_count`\n- Confusion Matrix Statistics:\n- `tool_calls_finish_tool_calls`: expected tool_call, actual tool_call (TP)\n- `tool_calls_finish_stop`: expected tool_call, actual stop (FN)\n- `stop_finish_tool_calls`: expected stop, actual tool_call (FP)\n- `stop_finish_stop`: expected stop, actual st"},{"ref":"P14","kind":"page","title":"MiniMax-AI/Mini-Agent repository metadata","date":"2026-06-11T03:57:40.607555+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/Mini-Agent","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/Mini-Agent\n\nDescription: A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade features of agents.\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 2768\n\nForks: 413\n\nOpen issues: 37\n\nCreated: 2025-10-31T03:56:27Z\n\nPushed: 2026-02-14T04:00:26Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Mini Agent\n\nEnglish | [中文](./README_CN.md)\n\n**Mini Agent** is a minimal yet professional demo project that showcases the best practices for building agents with the MiniMax M2.5 model. Leveraging an Anthropic-compatible API, it fully supports interleaved thinking to unlock M2's powerful reasoning capabilities for long, complex tasks.\n\nThis project comes packed with features designed for a robust and intelligent agent development experience:\n\n* ✅ **Full Agent Execution Loop**: A complete and reliable foundation with a basic toolset for file system and shell operations.\n* ✅ **Persistent Memory**: An active **Session Note Tool** ensures the agent retains key information across multiple sessions.\n* ✅ **Intelligent Context Management**: Automatically summarizes conversation history to handle contexts up to a configurable token limit, enabling infinitely long tasks.\n* ✅ **Claude Skills Integration**: Comes with 15 professional skills for documents, design, testing, and development.\n* ✅ **MCP Tool Integration**: Natively supports MCP for tools like knowledge graph access and web search.\n* ✅ **Comprehensive Logging**: Detailed logs for every request, response, and tool execution for easy debugging.\n* ✅ **Clean & Simple Design**: A beautiful CLI and a codebase that is easy to understand, making it the perfect starting point for building advanced agents.\n\n## Table of Contents\n\n- [Mini Agent](#mini-agent)\n- [Table of Contents](#table-of-contents)\n- [Quick Start](#quick-start)\n- [1. Get API Key](#1-get-api-key)\n- [2. Choose Your Usage Mode](#2-choose-your-usage-mode)\n- [🚀 Quick Start Mode (Recommended for Beginners)](#-quick-start-mode-recommended-for-beginners)\n- [🔧 Development Mode](#-development-mode)\n- [ACP \\& Zed Editor Integration(optional)](#acp--zed-editor-integrationoptional)\n- [Usage Examples](#usage-e"},{"ref":"P15","kind":"page","title":"MiniMax-AI/MiniMax-Coding-Plan-MCP repository metadata","date":"2026-06-11T03:57:40.479149+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/MiniMax-Coding-Plan-MCP","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/MiniMax-Coding-Plan-MCP\n\nDescription: Specialized MiniMax Model Context Protocol (MCP) server designed for coding-plan users, featuring AI-powered search and vision analysis APIs optimized for code development workflows\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 91\n\nForks: 24\n\nOpen issues: 11\n\nCreated: 2025-11-20T04:48:05Z\n\nPushed: 2026-02-10T12:01:59Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n\n\n
\n\n## News\n\n- **[2026.03.09]** We have updated our technical report with more experimental results.\n\n- **[2025.12.16]** We have released our [technical report](https://arxiv.org/abs/2512.13687) and [pretrained weights](#get-checkpoints).\n\n## Takeaways\n\nBy integrating contrastive, self-supervised, and reconstruction learning, we have trained numerous "},{"ref":"P17","kind":"page","title":"MiniMax-AI/vercel-minimax-ai-provider repository metadata","date":"2026-06-11T03:57:40.318489+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/vercel-minimax-ai-provider","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/vercel-minimax-ai-provider\n\nDescription: minimax-ai-provider is a community provider that use minimax-m2 to provide language model support for the AI SDK.\n\nLanguage: TypeScript\n\nLicense: Apache-2.0\n\nStars: 12\n\nForks: 5\n\nOpen issues: 1\n\nCreated: 2025-12-03T12:24:09Z\n\nPushed: 2026-06-06T07:41:49Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# AI SDK - MiniMax AI Provider\n\nThe **[MiniMax AI Provider](https://ai-sdk.dev/providers/community-providers/minimax)** for the [AI SDK](https://ai-sdk.dev/docs) contains language, image, speech, and video model support for the [MiniMax](https://www.minimax.io/) platform.\n\n## Available Models\n\n### Language\n\n- **MiniMax-M2**: Agentic capabilities, Advanced reasoning\n- **MiniMax-M2-Stable**: High concurrency and commercial use\n\nBoth models share the same API interface and usage patterns.\n\n### Image, Speech & Video\n\n- **Image**: `image-01`, `image-01-live` (text-to-image and image-to-image)\n- **Speech**: `speech-2.8-hd`/`-turbo`, `speech-2.6-hd`/`-turbo`, `speech-02-hd`/`-turbo` (text-to-speech)\n- **Video**: `MiniMax-Hailuo-2.3`, `MiniMax-Hailuo-02` (text/image-to-video), `MiniMax-Hailuo-2.3-Fast` (image-to-video)\n\nSee [Image, Speech & Video](#image-speech--video) below for usage.\n\n## Setup\n\n```bash\nnpm i vercel-minimax-ai-provider\n```\n\n## Provider Instance\n\nYou can import the default provider instance `minimax` from `vercel-minimax-ai-provider`:\n\n```ts\nimport { minimax } from 'vercel-minimax-ai-provider';\n```\n\n> **Note**: The default `minimax` instance uses the Anthropic-compatible API format, which provides better support for advanced features. If you need the OpenAI-compatible format, use `minimaxOpenAI` instead.\n\n## Example\n\n```ts\nimport { minimax } from 'vercel-minimax-ai-provider';\nimport { generateText } from 'ai';\n\nconst { text } = await generateText({\nmodel: minimax('MiniMax-M2'),\nprompt: 'Write a JavaScript function that sorts a list:',\n});\n```\n\n## API Compatibility\n\nMiniMax provides two API compatibility modes, both included in this package:\n\n### Anthropic-Compatible API (Default)\n\n```ts\nimport { minimax } from 'vercel-minimax-ai-provider';\nimport { generateText } from 'ai';\n\nconst { text } = awai"},{"ref":"P18","kind":"page","title":"MiniMax-AI/cli v1.0.12","date":"2026-06-11T03:45:01.165469+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/cli/releases/tag/v1.0.12","signal_url":null,"signal_json_url":null,"text":"# v1.0.12\n\nRepository: MiniMax-AI/cli\n\nTag: v1.0.12\n\nPublished: 2026-04-26T01:40:29Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* fix: inherit terminal foreground color in quota table by @JochenYang in https://github.com/MiniMax-AI/cli/pull/106\n* fix: validate explicit Hailuo fast I2V usage by @JochenYang in https://github.com/MiniMax-AI/cli/pull/108\n* test: add parseSSE coverage (src/client/stream.ts) by @hell0gunawan in https://github.com/MiniMax-AI/cli/pull/110\n* fix: resolve merge conflicts for PR #94 and complete SKILL.md docs by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/113\n* fix: force HTTPS for image downloads and add base64 response format by @nguyenngothuong in https://github.com/MiniMax-AI/cli/pull/94\n* fix(image): add --out flag for saving to exact file path by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/114\n* chore: bump version to 1.0.12 by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/115\n\n## New Contributors\n* @hell0gunawan made their first contribution in https://github.com/MiniMax-AI/cli/pull/110\n* @nguyenngothuong made their first contribution in https://github.com/MiniMax-AI/cli/pull/94\n\n**Full Changelog**: https://github.com/MiniMax-AI/cli/compare/v1.0.11...v1.0.12"},{"ref":"P19","kind":"page","title":"MiniMax-AI/cli v1.0.13","date":"2026-06-11T03:45:01.143677+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/cli/releases/tag/v1.0.13","signal_url":null,"signal_json_url":null,"text":"# v1.0.13\n\nRepository: MiniMax-AI/cli\n\nTag: v1.0.13\n\nPublished: 2026-05-11T02:50:00Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* fix derive CLI version from package metadata by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/121\n* fix: reject invalid numeric flags by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/120\n* feat: support SDK by @FliPPeDround in https://github.com/MiniMax-AI/cli/pull/122\n* refactor: deduplicate shared utilities across commands and SDK by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/125\n* feat: add HTTP/HTTPS proxy support via undici ProxyAgent by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/126\n* fix: protect downloads and stream JSON output by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/124\n* feat: audio format validation aligned with latest T2A API by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/127\n* release: v1.0.13 — audio format validation & lint cleanup by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/128\n\n## New Contributors\n* @FliPPeDround made their first contribution in https://github.com/MiniMax-AI/cli/pull/122\n\n**Full Changelog**: https://github.com/MiniMax-AI/cli/compare/v1.0.12...v1.0.13"},{"ref":"P20","kind":"page","title":"MiniMax-AI/cli v1.0.14","date":"2026-06-11T03:45:01.073488+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/cli/releases/tag/v1.0.14","signal_url":null,"signal_json_url":null,"text":"# v1.0.14\n\nRepository: MiniMax-AI/cli\n\nTag: v1.0.14\n\nPublished: 2026-05-17T08:02:47Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* fix: decode SSE audio stream for music and speech by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/130\n* fix: register file commands, fix endpoints, harden SSE & region validation by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/131\n* fix: preserve search shorthand with aliases by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/137\n* feat(auth): add OAuth device-code login (Global / CN) into config.json by @kapelame in https://github.com/MiniMax-AI/cli/pull/139\n* feat: replace raw thinking output with animated color-cycling indicator by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/149\n* feat: add interactive multi-turn chat REPL (mmx text repl) by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/141\n* test: add unit tests for OAuth device-code login flow by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/152\n* test: add unit tests for music cover, speech voices, and config export-schema by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/151\n* feat: add audio file save support to SpeechSDK and MusicSDK by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/147\n* feat: add image download and save support to ImageSDK by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/145\n* feat: add FileSDK module for file storage operations by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/143\n\n## New Contributors\n* @kapelame made their first contribution in https://github.com/MiniMax-AI/cli/pull/139\n\n**Full Changelog**: https://github.com/MiniMax-AI/cli/compare/v1.0.13...v1.0.14\n\n## What's Changed\n* fix: decode SSE audio stream for music and speech by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/130\n* fix: register file commands, fix endpoints, harden SSE & region validation by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/131\n* fix: preserve search shorthand with aliases by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/137\n* feat(auth): add OAuth device-code login (Global / CN) into config.json by @kapelame in https://github.com/MiniMax-AI/cli/pull/139\n*"},{"ref":"P21","kind":"page","title":"MiniMax-AI/cli v1.0.15","date":"2026-06-11T03:45:00.840497+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/cli/releases/tag/v1.0.15","signal_url":null,"signal_json_url":null,"text":"# v1.0.15\n\nRepository: MiniMax-AI/cli\n\nTag: v1.0.15\n\nPublished: 2026-05-17T08:14:24Z\n\nPrerelease: no\n\nRelease notes:\n**Full Changelog**: https://github.com/MiniMax-AI/cli/compare/v1.0.14...v1.0.15"},{"ref":"P22","kind":"page","title":"MiniMaxAI/MiniMax-Text-01 model card","date":"2026-06-11T03:03:59.686694+00:00","date_source":null,"source_url":"https://huggingface.co/MiniMaxAI/MiniMax-Text-01/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\npipeline_tag: text-generation\n---\n
\n\n# Meet MiniMax-M2.1\n\nToday, we are handing **MiniMax-M2.1** over to the open-source community. This release is more than just a parameter update; it is a significant step toward democratizing top-tier agentic capabilities.\n\nM2.1 was built to shatt"},{"ref":"P25","kind":"page","title":"MiniMax-AI/mini-vela repository metadata","date":"2026-06-11T03:02:50.994268+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/mini-vela","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/mini-vela\n\nLanguage: Python\n\nStars: 36\n\nForks: 5\n\nOpen issues: 1\n\nCreated: 2026-01-15T08:58:19Z\n\nPushed: 2026-04-02T13:09:54Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# mini-vela\n\n[](https://arxiv.org/abs/2601.10343)\n[](https://huggingface.co/datasets/MiniMaxAI/OctoBench)\n[](LICENSE)\n\n[English](README.md) | [中文](README_CN.md)\n\n## 📰 News\n\n- **[2026-01-16]** 📄 Paper released on arXiv: [OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding](https://arxiv.org/abs/2601.10343)\n- **[2026-01]** 🎉 Dataset & Framework released\n\n---\n\nA benchmark framework for evaluating instruction-following capabilities of AI Coding Agents. It intercepts API calls via LiteLLM Proxy, collects complete interaction trajectories, and performs automated scoring using LLM.\n\n## 🌟 Features\n\n- **Multi-Scaffold Support**: Supports Claude Code, Kilo-Dev, Droid and other AI development tools\n- **Trajectory Collection**: Automatically intercepts and records complete API call trajectories\n- **Automated Evaluation**: Multi-dimensional scoring of trajectories using LLM based on Checklist\n- **Docker Isolation**: Each task instance runs in an isolated container with a clean environment\n\n## 🏗️ Core Pipeline\n\n1. **Proxy Startup**: LiteLLM Proxy runs on the host machine, intercepting all API calls\n2. **Task Execution**: Scaffolds (Claude Code, Kilo, Droid) complete tasks in Docker containers\n3. **Trajectory Collection**: Each API request/response is recorded to individual JSONL files (raw trajectories)\n4. **Trajectory Processing**: Use `convert/` tools to deduplicate and merge raw trajectories into complete conversation trajectories\n5. **Automated Evaluation**: Score merged trajectories using LLM based on Checklist\n\n## 🚀 Quick Start\n\n### Prerequisites\n\n- Python 3.11+\n- Docker\n- LLM API Key (Anthropic / MiniMax / Gemini, etc.)\n\n### Install Dependencies\n\n```bash\npip install -r requirements.txt\n```\n\n### Configure API Keys\n\n```bash\ncd pr"},{"ref":"P26","kind":"page","title":"MiniMax-AI/cli v1.0.16","date":"2026-06-11T02:59:44.997843+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/cli/releases/tag/v1.0.16","signal_url":null,"signal_json_url":null,"text":"# v1.0.16\n\nRepository: MiniMax-AI/cli\n\nTag: v1.0.16\n\nPublished: 2026-06-01T10:35:24Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* test: comprehensive test coverage improvements (pure functions, SDK validation, command tests) by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/156\n* feat: use coding plan quota remains by @JochenYang in https://github.com/MiniMax-AI/cli/pull/166\n* bump version to v1.0.16 by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/167\n\n**Full Changelog**: https://github.com/MiniMax-AI/cli/compare/v1.0.15...v1.0.16\n\n## What's Changed\n* test: comprehensive test coverage improvements (pure functions, SDK validation, command tests) by @NianJiuZst in https://github.com/MiniMax-AI/cli/pull/156\n* feat: use coding plan quota remains by @JochenYang in https://github.com/MiniMax-AI/cli/pull/166\n* bump version to v1.0.16 by @RyanLee-Dev in https://github.com/MiniMax-AI/cli/pull/167\n\n**Full Changelog**: https://github.com/MiniMax-AI/cli/compare/v1.0.15...v1.0.16"},{"ref":"P27","kind":"page","title":"MiniMax-AI/vllm repository metadata","date":"2026-06-11T02:54:15.179018+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/vllm","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/vllm\n\nDescription: A high-throughput and memory-efficient inference and serving engine for LLMs\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 17\n\nForks: 11\n\nOpen issues: 0\n\nCreated: 2025-04-21T12:30:16Z\n\nPushed: 2025-10-26T16:08:09Z\n\nDefault branch: main\n\nFork: yes\n\nParent repository: vllm-project/vllm\n\nArchived: no\n\nREADME:\n\n
\n\n\n\n\n
\n\n
\nEasy, fast, and cheap LLM serving for everyone\n
\n\n---\nJoin us at the [PyTorch Conference, October 22-23](https://events.linuxfoundation.org/pytorch-conference/) and [Ray Summit, November 3-5](https://www.anyscale.com/ray-summit/2025) in San Francisco for our latest updates on vLLM and to meet the vLLM team! Register now for the largest vLLM community events of the year!\n\n---\n\n*Latest News* 🔥\n\n- [2025/09] We hosted [vLLM Toronto Meetup](https://luma.com/e80e0ymm) focused on tackling inference at scale and speculative decoding with speakers from NVIDIA and Red Hat! Please find the meetup slides [here](https://docs.google.com/presentation/d/1IYJYmJcu9fLpID5N5RbW_vO0XLo0CGOR14IXOjB61V8/edit?usp=sharing).\n- [2025/08] We hosted [vLLM Shenzhen Meetup](https://mp.weixin.qq.com/s/k8ZBO1u2_2odgiKWH_GVTQ) focusing on the ecosystem around vLLM! Please find the meetup slides [here](https://drive.google.com/drive/folders/1Ua2SVKVSu-wp5vou_6ElraDt2bnKhiEA).\n- [2025/08] We hosted [vLLM Singapore Meetup](https://www.sginnovate.com/event/vllm-sg-meet). We shared V1 updates, disaggrega"},{"ref":"P28","kind":"page","title":"MiniMax-AI/MiniMax-M2.5 repository metadata","date":"2026-06-11T02:53:01.674381+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/MiniMax-M2.5","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/MiniMax-M2.5\n\nLicense: NOASSERTION\n\nStars: 585\n\nForks: 77\n\nOpen issues: 29\n\nCreated: 2026-02-13T04:47:29Z\n\nPushed: 2026-03-09T02:44:20Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n
![\"MiniMax\"](\"figures/MiniMaxLogo-Dark.png\")
\n![\"Homepage\"](\"https://img.shields.io/badge/_Homepage-MiniMax-FF4040?style=flat-square&labelColor=2C3E50&logo=data:image/svg+xml;base64,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&logoWidth=20\"){kind=icon}
\n\n\n![\"MiniMax\"](\"assets/images/MiniMaxLogo-Dark.png\")
\n![\"Paper\"](\"https://img.shields.io/badge/📖_Paper-MiniMax--01-FF4040?style=flat-square&labelCo"},{"ref":"P5","kind":"page","title":"MiniMax-AI/MiniMax-AI.github.io){kind=icon}
\n![\"Alipay\"](\"assets/images/alipay.png\")
![](\"assets/images/wps.png\")
\n![\"MiniMax\"](\"assets/minimax-logo.png\"){kind=logo}
\n![\"Paper](\"https://img.shields.io/badge/📖_Paper-PDF-327DE6?style=flat-square&labelColor=2C3E50\"){kind=icon}
\n![\"Paper\"](\"https://img.shields.io/badge/📖_Paper-Arxiv-327DE6?style=flat-square&labelColor=2C3E50\"){kind=icon}
\n![\"Hugging](\"https://img.shields.io/badge/🤗_HF-Model-327DE6?style=flat-square&labelColor=2C3E50\"){kind=icon}
\n![\"Hugging](\"https://img.shields.io/badge/🤗_HF-Data-327DE6?style=flat-square&labelColor=2C3E50\"){kind=icon}
\n![\"Model](\"https://img.shields.io/badge/License-MIT-327DE6?style=flat-square&labelColor=2C3E50\"){kind=icon}
\n![\"Laser](\"assets/main.jpg\")
\n![\"Paper\"](\"https://img.shields.io/badge/📖_Paper-MiniMax"},{"ref":"P10","kind":"page","title":"MiniMax-AI/MiniMax-Hackathon){kind=icon}
\n\n### SHORTR\n\n[GitHub](https://github.com/boopesh07/VideoToShorts) | [Youtube](https://www.youtube.com/watch?v=4PowXXv43us)\n\n### Know the past\n\n[GitHub](https://github.com/Prasanna721/hack-know-the-past) | [Youtube](https://www.youtube.com/watch?v=sCBF-bdD4Og)\n\n### Viral Video Creator\n\n[GitHub]() | [Youtube](https://www.youtube.com/watch?v=ZFHexXujtso)"},{"ref":"P11","kind":"page","title":"MiniMax-AI/MiniMax-M2 repository metadata","date":"2026-06-11T03:57:41.493252+00:00","date_source":null,"source_url":"https://github.com/MiniMax-AI/MiniMax-M2","signal_url":null,"signal_json_url":null,"text":"# MiniMax-AI/MiniMax-M2\n\nDescription: MiniMax-M2, a model built for Max coding & agentic workflows.\n\nLicense: NOASSERTION\n\nStars: 2596\n\nForks: 215\n\nOpen issues: 55\n\nCreated: 2025-10-25T21:28:29Z\n\nPushed: 2025-11-13T08:12:36Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n![\"Paper\"](\"https://img.shields.io/badge/📖_Paper-MiniM"},{"ref":"P16","kind":"page","title":"MiniMax-AI/VTP){kind=icon}
\n\n![\"Logo\"](\"figures/logo.png\"){kind=logo}
\n\n![\"Abstract](\"figures/abs.png\")
\n\n![\"vLLM\"](\"https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png\"){kind=logo}
\n![](\"figures/bench_11.png\")
\n