Multi-agent and orchestration

Harnesses and patterns for multi-agent coordination and handoffs.

#ProjectStarsTierOSSDescription
1MetaGPT
multi-agentpython
69.6kcomplexThe "AI software company" multi-agent framework: role-played PM, architect, and engineer agents turn a one-line requirement into specs, designs, and code along an SOP assembly line. The landmark of the genre; development pace has slowed in 2026.
2autogen
multi-agentpython
60.2kcomplex✅ CC-BYConversable agents and group chats; code execution and human-in-the-loop; Microsoft origin, AG2 ecosystem.
3OpenManus
multi-agentpython
57.8kcomplexOpen, invite-free general agent from the MetaGPT team: planning plus tool use over a multi-agent loop, aimed at reproducing Manus-style autonomous task completion on your own keys.
4crewAI
python
56.5kcomplexRole-based agents (roles, goals, backstories) in Crews; Flows add event-driven and hierarchical control for production.
5ChatDev
python
33.9kslightly complexMulti-agent software-company simulation (CEO, CTO, programmer, tester) built on chat chains with communicative dehallucination; ChatDev 2.0 continues the line. MetaGPT's conversational sibling.
6openai-agents-python
python
28.3kmostly simpleHandoffs, guardrails, and multi-LLM routing; minimal surface so you own the loop.
7Microsoft Agent Framework
multi-agentworkflowpython
12.5kslightly complexMicrosoft's convergence of AutoGen and Semantic Kernel: build, orchestrate, and deploy agents and multi-agent workflows in Python and .NET, with graph-based workflows and checkpointing — the designated successor harness for both lines.
8hive
multi-agentpython
10.8kcomplexSelf-hosted multi-agent **harness** aimed at production workloads: human-in-the-loop checkpoints and a self-improving agent loop, distinct from single-session coding-agent shells.
9PraisonAI
multi-agentpython
8.5kmostly simpleAutonomous multi-agent teams with a single entry point; emphasis on minimal config.
10omnigent
sandboxidepython
8kcomplexOpen-source meta-**harness**: orchestrates Claude Code, Codex, Cursor, Pi, and custom agents behind one policy/sandboxing layer so teams swap harnesses without rewriting workflows.
11AG2
multi-agentpython
4.8kcomplexAG2 (formerly AutoGen): the community-governed continuation of the original AutoGen project after Microsoft's fork diverged—conversable multi-agent groups, code execution, and human-in-the-loop under an open-source AgentOS banner. Graduated off the radar this cycle.
12AgentRL
trainingpython
330complexMultitask, multiturn RL for LLM agents; Ray-based scaling, rollout/actor workers—for teams that want to train agents, not just run them.