Skip to content
repository radar
Agents & Orchestration

AutoGen

ACTIVE STEADY

microsoft/autogen · homepage ↗

A programming framework for agentic AI

⭐ Hugely popular: 60k stars, gaining about 128 a week

View on GitHub ↗

repo profile

vintage 2023 3 years old
language Python
license CC-BY-4.0

momentum

total stars 60k
stars added last week +128
HN peak 163 pts 2y 10mo ago
used by 4k repos & packages
commits / week 0 steady
issues closed 31% ~4d to close, median
contributors 534
release cadence fortnightly
last activity 4mo ago

durability

backing company-owned Microsoft
openness permissive
security score 5.6/10 OpenSSF Scorecard · 2026-08-10

since we covered it

monthly average + 1k/mo (+3%/mo) · + 20k total since PR#3

why it's a big deal

  • Provides an open-source, scalable solution for automating complex cognitive tasks through coordinated AI agents.
  • Enables developers to orchestrate sophisticated, multi-agent interactions, significantly reducing manual interventions.
  • Supports integration with leading LLMs (like GPT-4), enhancing flexibility and performance across diverse applications.

under the hood

  • Built on Python, facilitating easy adoption and integration into existing codebases.
  • Supports direct integration with popular LLMs through frameworks like LangChain, making it versatile across AI ecosystems.
  • Enables creation of customisable agents and workflows, allowing detailed control over AI-driven processes.

our take from PR#3, 2025-03-05

star history

PR#3 · 41k60k now Aug 2023Aug 2026
  1. PR#3 41k 2025-03-05
  2. now 60k + 20k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Better known than its recent output, coasting a little on attention.

-70 understory score output 0 · clout 70
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#3 2025-03-05 above the radar

    Automate Complex Workflows with Multi-Agent LLMs

similar projects

compare these →
  • 🧠 LangGraph

    Build resilient agents.

    40k ACTIVE
  • VoltAgent

    TypeScript · leaner, 10k stars

    AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

    10k ACTIVE
  • 🦾 OpenAI Agents

    leaner, 29k stars

    A lightweight, powerful framework for multi-agent workflows

    29k ACTIVE

comments

Sign in with GitHub to add your blip on AutoGen.

loading comments…