# microsoft/autogen

A programming framework for agentic AI

Repository: https://github.com/microsoft/autogen
Canonical: https://ross.abutalabs.com/products/autogen
Homepage: https://microsoft.github.io/autogen/
Language: Python
License: CC-BY-4.0
License Family: other
Topics: chatgpt, llm-agent, llm-framework, agentic, agentic-agi, agents, ai, autogen, framework, autogen-ecosystem
Last push: 2026-04-15T11:59:09+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 77, release rhythm 50, longevity 79
- inputs: {"age_days": 1111, "days_push": 140, "days_rel": 337, "gap_med": 6, "n_releases_24m": 36}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 60643, forks 9154 (observed 2026-08-28T04:12:18.832983+00:00)

## What it is
AutoGen is a Python framework from Microsoft for building multi-agent AI applications where LLM-powered agents can act autonomously or collaborate with humans. It is now in maintenance mode, with Microsoft Agent Framework as its production-ready successor.

## Use cases
- build multi-agent ai applications
- orchestrate llm agents that talk to each other
- create autonomous ai agents in python
- prototype agent workflows with gpt-4o
- build agents with no-code gui
- add human-in-the-loop to ai agents

## When to choose
- you need a mature, widely-adopted multi-agent framework in Python
- you want AutoGen Studio's no-code agent prototyping
- you have existing AutoGen v0.2 code to maintain

## When to avoid
- you are starting a new project - use Microsoft Agent Framework instead
- you need new features or long-term support commitments
- you need enterprise-grade multi-agent orchestration with A2A/MCP interoperability

## Facets
- artifact type: framework
- maturity: maintenance
- function: agent-framework, llm-inference, chatbot, workflow-automation, mcp
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python, cross-platform
- tags: multi-agent, llm-agents, agentic-ai, autogen-studio, no-code-gui, microsoft, successor-agent-framework, ai-agents

## Member repositories
- microsoft/autogen (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:18.832983+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:17:46.617096+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/autogen (fetched 2026-08-28T04:12:18.832983+00:00, sha 18fd1c3f71d8)
  - homepage: https://microsoft.github.io/autogen/ (fetched 2026-08-28T17:59:25.329851+00:00, sha c25f3aa58fc8)
- Data as of 2026-08-30T08:39:29.467469+00:00.