Registry / llm-agents / autogen-agentchat

autogen-agentchat

library0.7.5pypypi✓ verified 26d ago

Microsoft's framework for building multi-agent AI applications. As of v0.4+, AutoGen is a layered system: autogen-core (event-driven actor runtime), autogen-agentchat (high-level conversational agents), and autogen-ext (extensions for OpenAI, Azure, MCP, etc.). Completely async. The 0.2 API is a separate, deprecated architecture. NOT the same as AG2.

llm-agents ai-ml

pip install -U "autogen-agentchat" "autogen-ext[openai]"

package ↗homepage ↗

INSTALL

IMPORT

SIG · AUTOGEN-AGENTCHAT

autogen-agentchat

llm-agentspythonv0.7.5

Install

—

Import

—

Disk

—

Pass rate

0/ 10

Env Coverage0 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.7.5 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

16/18 runs

py 3.11

10/18 runs

16/18 runs

py 3.12

16/18 runs

py 3.13

10/18 runs

16/18 runs

py 3.9

12/18 runs

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

AssistantAgent (v0.4+)

✓ from autogen_agentchat.agents import AssistantAgent from autogen_ext.models.openai import OpenAIChatCompletionClient

✗ from autogen.agentchat import AssistantAgent from autogen.oai import OpenAIWrapper

The v0.2 import paths (autogen.agentchat, autogen.oai) are completely different from v0.4+. Mixing them causes immediate ImportError or silent wrong behavior.

RoutedAgent (Core API)

✓ from autogen_core import RoutedAgent, message_handler

✗ from autogen_core.components import RoutedAgent

RoutedAgent is in autogen_core directly, not autogen_core.components. LLM-generated code frequently gets this wrong.

Single AssistantAgent with OpenAI — v0.4+ API

import asyncio from autogen_agentchat.agents import AssistantAgent from autogen_ext.models.openai import OpenAIChatCompletionClient async def main() -> None: model_client = OpenAIChatCompletionClient(model='gpt-4o') agent = AssistantAgent('assistant', model_client=model_client) result = await agent.run(task='Say Hello World!') print(result) await model_client.close() asyncio.run(main())

Debug

Known issues

breakingAutoGen v0.4+ is a complete ground-up rewrite with a fully incompatible API from v0.2. All v0.2 imports (from autogen.agentchat, autogen.oai, AssistantAgent with llm_config dict, UserProxyAgent) are broken in v0.4.

fix

Follow the official migration guide: https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/migration-guide.html

affects: >=0.4.0

breakingAll v0.4+ AutoGen APIs are fully async. Calling agent.run() without await in an async context, or calling it in a sync context without asyncio.run(), will fail or produce no output.

fix

Always use asyncio.run(main()) at the entry point. Use await for all agent calls.

affects: >=0.4.0

breakingOpenAIChatCompletionClient is in autogen-ext, not autogen-agentchat. pip install autogen-agentchat alone is insufficient — model clients require autogen-ext[openai] or the relevant provider extra.

fix

pip install 'autogen-ext[openai]' for OpenAI/OpenAI-compatible models. Use 'autogen-ext[azure]' for Azure OpenAI, 'autogen-ext[anthropic]' for Claude.

affects: >=0.4.0

breakingpyautogen on PyPI is no longer maintained by Microsoft as of v0.2.34+. Control of that package was lost to an AG2-affiliated fork. Do not use pyautogen for Microsoft AutoGen.

fix

Install via autogen-agentchat (for v0.4+) or autogen-agentchat~=0.2 (for legacy v0.2). Never use pyautogen.

affects: all

gotchaAG2 (pip install ag2 or pip install autogen) is a community fork of AutoGen 0.2, NOT Microsoft's AutoGen 0.4. The autogen PyPI package is currently controlled by the AG2 project. Code written for AG2 and code written for Microsoft AutoGen 0.4 are NOT compatible.

fix

For Microsoft AutoGen 0.4+, install autogen-agentchat and autogen-ext. For AG2/legacy API, install ag2 or pin autogen-agentchat~=0.2.

affects: all

gotchaLLM-generated AutoGen code is highly unreliable. Most AI assistants (as of early 2026) mix v0.2 and v0.4 imports, use wrong module paths (autogen_core.components vs autogen_core), or use synchronous patterns on async-only APIs.

fix

Always verify against the official docs at https://microsoft.github.io/autogen/stable/

affects: >=0.4.0

gotchamodel_client.close() must be explicitly called after use to avoid resource leaks. The client does not auto-close.

fix

Use try/finally or async context managers: async with OpenAIChatCompletionClient(...) as client: ...

affects: >=0.4.0

breakingInstalling certain dependencies (e.g., numpy, which is a dependency of tiktoken used by autogen-ext[openai]) in minimal Linux environments like Alpine requires build tools. Without them, package installation will fail due to missing compilers.

fix

Ensure that necessary build tools are installed in your environment. For Alpine Linux, this typically means running `apk add build-base` before installing Python packages. Example Dockerfile: `FROM python:3.13-alpine
RUN apk add build-base
RUN pip install autogen-agentchat 'autogen-ext[openai]'`

affects: all

Upgrade

Version history

0.7.5latest on PyPI · released Sep 30, 2025

Audit

Dependencies

autogen-ext[openai]requiredOpenAIChatCompletionClient lives in autogen-ext, not autogen-agentchat. Required for any OpenAI or OpenAI-compatible model use.

Python >=3.10requiredHard requirement across all autogen packages.

Agent activity

103 hits · last 30 days

node