ag2ai/ag2GitHub
Use as a drop-in, actively maintained continuation of AutoGen under Apache-2.0.
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
- 4.9k
- Python
- Apache-2.0
active30d ago
microsoft/autogen Alternatives
multi-agent AI framework
A programming framework for creating multi-agent AI applications that can act autonomously or work alongside humans.
Drop-in peers
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Same job, different approach
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
FareedKhan-dev/all-agentic-architecturesGitHub
Choose it to reuse proven agent architectures (Reflexion, LATS, etc.) as a Python library instead of building your own orchestration.
35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.
- 4.5k
- Jupyter Notebook
- MIT
active4mo ago
Older generation, or narrower
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
OpenBMB/ChatDevGitHub
Choose it if your multi-agent use case is specifically software development automation; it is narrower than AutoGen.
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
- 34.1k
- Python
- Apache-2.0
active3mo ago
End-user tools
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
crestalnetwork/intentkitGitHub
Choose it if you want a self-hosted, ready-to-deploy agent cluster rather than embedding a framework in your code.
IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.
- 6.5k
- Python
- MIT
active2mo ago
Listed as an alternative to
These projects were analysed and named autogen among their alternatives. The relationship is not symmetric — how autogen rates them is a separate judgement, made when autogen is analysed in its own right.
camel-ai/owlGitHub
calls autogen “Choose for a mature, widely-adopted Python multi-agent framework with large ecosystem and Microsoft support.”
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
20.1kPythonactive
Upsonic/UpsonicGitHub
calls autogen “When you want a widely adopted, battle-tested agent framework with rich multi-agent patterns.”
Build autonomous AI agents in Python.
7.9kPythonactive
agentuniverse-ai/agentUniverseGitHub
calls autogen “Choose autogen for Microsoft-backed Python multi-agent conversation patterns and a large ecosystem, accepting CC-BY-4.0 licensing quirks.”
agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.
2.4kPythonactive
shareAI-lab/learn-claude-codeGitHub
calls autogen “Choose for a production multi-agent framework with extensive features and ecosystem when you don't want to hand-roll a minimal harness.”
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
75.5kPythonactive
OpenBMB/ChatDevGitHub
calls autogen “Choose for a widely adopted Python framework for building agentic AI with fine-grained control.”
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
34.1kPythonactive
cft0808/edictGitHub
calls autogen “Mature programming framework for agentic AI; choose it for fine-grained control with Python code.”
🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails
16.9kPythonactive
dataelement/bishengGitHub
calls autogen “When you want a code-first agent programming framework instead of a full platform.”
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.
12.0kPythonactive
alibaba/spring-ai-alibabaGitHub
calls autogen “Python framework for multi-agent conversational AI; choose if you need a well-known research-oriented Python option.”
Agentic AI Framework for Java Developers
10.7kJavaactive
OpenBMB/XAgentGitHub
calls autogen “when you want a mature, conversational multi-agent framework from Microsoft instead of a ready-to-run autonomous agent.”
An Autonomous LLM Agent for Complex Task Solving
8.5kPythonactive
open-multi-agent/open-multi-agentGitHub
calls autogen “Python-based conversational multi-agent framework; choose it when your backend is Python and you prefer AutoGen's group-chat model over a TypeScript DAG scheduler.”
TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, DeepSeek, or local models).
6.8kTypeScriptactive
FareedKhan-dev/all-agentic-architecturesGitHub
calls autogen “Choose it for a mature conversation-based multi-agent framework, though its CC-BY-4.0 license differs from the seed's MIT.”
35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.
4.5kJupyter Notebookactive
google/adk-jsGitHub
calls autogen “Python multi-agent conversation framework; choose it if your team is Python-first and you want Microsoft's research-oriented agent model.”
An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
1.4kTypeScriptactive