inclusionAI/AEnvironment

inclusionAI/AEnvironment

Description: Standardized environment infrastructure for Agentic AI development.

Language: Python

License: Apache-2.0

Stars: 306

Forks: 36

Open issues: 14

Created: 2025-12-16T08:55:47Z

Pushed: 2026-05-22T04:07:07Z

Default branch: main

Fork: no

Archived: no

README:

AEnvironment

| Documentation | WeChat (微信) Group |

Everything as Environment — A Production-Grade Environment Platform for Agentic RL and Agent

---

📰 News

• Deploy Skill (Feb 2026) - 🎉 New Claude Code Skill for automated deployment! Deploy instances and services directly from Claude Code with support for three workflows: local build, existing image, and registered environments. [Get Started](#deploy-skill)
• v0.1.4 (Jan 2026) - AEnv CLI now supports instance and service management! Deploy and manage your agents and applications with simple commands. See [CLI Guide](./docs/guide/cli.md) for details.

---

About AEnvironment

AEnvironment is a unified environment platform for the Agentic RL era, built on the core philosophy of "Everything as Environment". By extending standardized MCP protocol, AEnvironment provides out-of-the-box infrastructure for environment providers, algorithm developers, and agent developers, allowing them to focus on agent capabilities rather than the tedious details of environment setup.

Within Ant Group, AEnvironment serves as a key environment layer technology, deeply integrated with the AReaL reinforcement learning framework, supporting large-scale Agentic RL training and agent service deployment.

Core Philosophy: Everything as Environment

AEnvironment abstracts everything as an environment—from simple tool functions to complex multi-agent systems, all accessible through a unified Environment interface. This unified abstraction enables capabilities to be registered, combined, and replaced like building blocks, seamlessly converging Benchmark integration, RL training, and agent deployment on the same infrastructure.

Key Features

🔧 Built-in Benchmarks, Zero-Cost Integration - Ready-to-use benchmark environments with no complex configuration. Currently supported: TAU2-Bench, SWE-Bench, and Terminal-Bench.

🚀 Seamless Agentic RL Training Integration - With native MCP support and OpenAI Agent SDK compatibility, you can focus on agent logic and seamlessly integrate into RL training workflows.

🤖 Agent as Environment - Treat agents as environments, enabling multi-agent orchestration. Compatible with mainstream agent frameworks including OpenAI Agents SDK.

⚡ Rapid Development to Production - Define tools, build, and deploy in seconds. AEnvironment provides a unified, low-threshold environment API abstraction, making environments no longer a bottleneck in the training pipeline.

Use Cases

Mini Program IDE

Build AI-powered mini-program generation systems where agents leverage AEnvironment as the standard environment infrastructure. The [Mini Program example](./aenv/examples/mini-program/) demonstrates:

• AEnvironment as Infrastructure: Agents utilize AEnvironment as the standardized environment infrastructure, providing consistent tooling and runtime capabilities
• AI Agent Integration: Multi-turn conversations powered by OpenAI API
• MCP Tools: File operations, code execution, and validation tools
• Live Preview: Real-time preview of generated applications

# The agent uses AEnvironment tools to create web applications
async with Environment("mini-program@1.0.0") as env:
# Agent can use tools like read_file, write_file, execute_python_code
result = await env.call_tool("write_file", {
"path": "index.html",
"content": "..."
})

📖 See [Mini Program Example](./aenv/examples/mini-program/README.md) for details.

TAU2 RL Training

Train reinforcement learning agents with AReaL framework using TAU2 tasks. The [TAU2 RL example](./aenv/examples/tau2_rl/) shows:

• RL Integration: Seamless integration with AReaL for agentic RL training
• Reward Function: Environment exposes reward functions for RL training
• Episode Runner: Turn-by-turn agent execution with automatic tool invocation
• Scalable Training: Support for large-scale distributed RL training

# Entrypoint for AReaL training
from aenv.examples.tau2_rl.agent import run_agent_return_reward

# Run a single episode and return reward
reward = await run_agent_return_reward({
"domain": "telecom",
"task_id": "task_123"
})

📖 See [TAU2 RL Example](./aenv/examples/tau2_rl/README.md) for details.

Agent as Environment

AEnvironment uniquely supports treating agents themselves as environments. This feature makes multi-agent orchestration, hierarchical agent systems, and agent adversarial testing possible.

With Agent as Environment, you can:

• Compose Agents: Treat agents as reusable components that can be called like tools
• Multi-Agent Orchestration: Build complex workflows where agents interact with each other
• Hierarchical Systems: Create nested agent structures for complex problem-solving

# Agent A calls Agent B as an environment
async with Environment("agent-b@1.0.0") as agent_b:
# List available tools from Agent B
tools = await agent_b.list_tools()

# Call Agent B's chat tool
response = await agent_b.call_tool("chat", {"message": "Hello!"})
print(response.content)

This design enables agents to be composed and orchestrated like environments, supporting complex multi-agent scenarios where agents can interact with each other through the same unified interface.

🎯 Built-in Environments

AEnvironment comes with several built-in environments ready to use:

| Environment | Description | Example | |-------------|-------------|---------| | TAU2 | This environment supports RL experiments with TAU2 benchmark | [tau2](./aenv/builtin-envs/tau2/) / [tau2_rl](./aenv/examples/tau2_rl/) | | Mini Terminal | Lightweight terminal environment with bash command execution support | [mini-terminal](./aenv/builtin-envs/mini-terminal/) | | TerminalBench | Supports running Terminal Bench evaluation | [terminalbench](./aenv/builtin-envs/terminalbench/) |

📖 See [Built-in Environments](./aenv/builtin-envs/) for more details.

Quick Start

📖 For detailed setup instructions, see the [Quick Start Guide](./docs/getting_started/quickstart.md).

Deploy Skill

The easiest way to deploy AEnvironment instances and services is using our Claude…