microsoft/autogen
Microsoft's agentic programming framework: conversation-based multi-agent patterns from the original research lineage, in transition toward its successor stack. Agentiquette scores it 75/100 (A-tier), methodology v1.0, scored 2026-07-07.
Key facts
| Category | Orchestration framework |
|---|---|
| License | CC-BY-4.0 |
| Maintainer | Microsoft |
| Compatible agents | generic |
| File patterns | |
| Triggering | manual-reference |
| GitHub metrics | 59,549 stars · 8,964 forks · 927 open issues (fetched 2026-07-07) |
| Last commit | 2026-04-15 |
| Created | 2023-08-18 |
Editorial analysis
Historically important: the repo that taught the ecosystem multi-agent conversation patterns. The 12-week commit gap at fetch time and Microsoft's visible consolidation toward newer agent tooling put a strategic question over new adoption that the code quality alone doesn't answer. Existing users are fine; new projects should ask what happens next.
Risks
Commit cadence slowed through 2026 as Microsoft's agent effort consolidates elsewhere; adopt with the succession question answered.
Evidence notes: Maintenance: 12-week commit gap at fetch, high open-issue count. Documentation: mature and complete. Reliability: termination conditions and reply functions are explicit.
Install and first run
pip install autogen-agentchatAlternatives in this category
The most adopted graph-based agent orchestration framework: workflows as explicit state machines with checkpointing, human-in-the-loop…
An agent framework built on type validation: structured outputs, dependency injection, and tool schemas checked the way Pydantic checks…
OpenAI's first-party multi-agent framework: agents, handoffs, guardrails, and tracing in a deliberately small API surface.
Embed this badge
Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.
[](https://agentiquette.com/index/repos/autogen)Frequently asked questions
Is microsoft/autogen good?
microsoft/autogen scores 75/100 (A-tier) on Agentiquette's methodology v1.0, scored 2026-07-07. Strengths and weaknesses are in the editorial analysis; the score is explained dimension by dimension in the scorecard.
What is microsoft/autogen for?
Microsoft's agentic programming framework: conversation-based multi-agent patterns from the original research lineage, in transition toward its successor stack.
Is microsoft/autogen maintained?
Last commit 2026-04-15, 927 open issues at fetch time (2026-07-07). Maintenance is scored at 60 of 100.
Maintainer of microsoft/autogen? Claim this listing and suggest corrections.