Multi-agent and orchestration
Harnesses and patterns for multi-agent coordination and handoffs.
| # | Project | Stars | Tier | OSS | Description |
|---|---|---|---|---|---|
| 1 | MetaGPT multi-agentpython | 71.1k | complex | ✅ | The "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. |
| 2 | autogen multi-agentpython | 61.7k | complex | ✅ CC-BY | Conversable agents and group chats; code execution and human-in-the-loop; Microsoft origin, AG2 ecosystem. ⚠️ In maintenance mode since late 2025: no new features, and Microsoft directs new users to Agent Framework. |
| 3 | crewAI python | 60.4k | complex | ✅ | Role-based agents (roles, goals, backstories) in Crews; Flows add event-driven and hierarchical control for production. |
| 4 | OpenManus multi-agentpython | 58.9k | complex | ✅ | Open, 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. |
| 5 | ChatDev python | 34.6k | slightly complex | ✅ | Multi-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. |
| 6 | openai-agents-python python | 30.4k | mostly simple | ✅ | Handoffs, guardrails, and multi-LLM routing; minimal surface so you own the loop. |
| 7 | Microsoft Agent Framework multi-agentworkflowpython | 14.5k | slightly complex | ✅ | Microsoft'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. |
| 8 | omnigent sandboxidepython | 11.2k | complex | ❓ | Open-source meta-**harness**: orchestrates Claude Code, Codex, Cursor, Pi, and custom agents behind one policy/sandboxing layer so teams swap harnesses without rewriting workflows. |
| 9 | hive multi-agentpython | 11.1k | complex | ❓ | Self-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. |
| 10 | PraisonAI multi-agentpython | 9.3k | mostly simple | ✅ | Autonomous multi-agent teams with a single entry point; emphasis on minimal config. |
| 11 | Orkas memorymulti-agenttypescript | 7.2k | complex | ✅ | Local-first desktop AI team. The **harness** is a Commander agent that turns one chat goal into a plan and runs specialist agents in parallel or in sequence, with tool approvals, session checkpoints, tool-round budgets and idle watchdogs for stalled runs, durable per-agent memory, and support for built-in or external agent runtimes. |
| 12 | Open Multi-Agent multi-agentlow-codeworkflowtypescript | 7k | slightly complex | ✅ | Self-hosted TypeScript multi-agent runtime. The **harness** is a coordinator that plans a task DAG from one goal at runtime and a deterministic scheduler that runs specialized agents, with durable approvals that pause before a plan, task, or tool call, PostgreSQL-backed checkpoints for restart recovery, and a verifiable run journal for replay; `runTasks()` keeps the graph fixed when the topology must not change. |
| 13 | Raven mcpmemorymulti-agentclipython | 6k | complex | ✅ | EverMind's host agent, with its loop split into memory, planning, capability, and action modules. The **harness** plans complex tasks as DAGs and orchestrates built-in research, coding, design, and on-call agents plus third-party agents (Claude Code, Codex, OpenClaw, Hermes Agent) over ACP, CLI, or OpenAI-compatible APIs, with long-term memory; labeled pre-alpha, with tagged releases since v0.1.0. |
| 14 | AG2 multi-agentpython | 5k | complex | ❓ | AG2 (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. |
| 15 | HarnessRouter memorysandboxpython | 3.8k | complex | ✅ | Self-hostable Community Edition of a unified interface for complete agent harnesses. The **harness** contribution is the layer around them: each task runs a full harness (Codex, Claude Code, Hermes, Pi, DeepSeek Harness, and others) in its own on-demand sandbox, the harness is a request parameter behind an OpenAI Responses-compatible API (the open Unified Harness Protocol), and the layer handles sessions, streaming, files, and traces. |
| 16 | Agent Teams AI multi-agentidetypescript | 2.4k | complex | ✅ | Desktop app that runs a team of coding agents (Claude Code, Codex, OpenCode, Cursor, Copilot, and others) on a kanban board: agents take tasks, message each other, and review each other's work before it is accepted. The **harness** contribution is the team-coordination layer over existing agent CLIs, with per-action approval or full autonomy; the kanban board is the shell. |
| 17 | CUGA mcpmulti-agentsandboxpython | 1.1k | mostly simple | ✅ | Open-source enterprise agent **harness**: a code-act loop in which the model writes Python that calls MCP, OpenAPI, and LangChain tools as functions inside a restricted sandbox, with results kept as variables, pre-execution verification, reflection, and tool shortlisting; CugaSupervisor coordinates multi-agent teams locally or over A2A, and runtime-enforced policies (intent guards, tool approvals, ToolGuard checks) gate what agents may do. Previously ranked #1 on the AppWorld and WebArena leaderboards; runs on open-weight or hosted models, including air-gapped deployments. Maintained by IBM and open to community contributions. |
| 18 | Desplega Agent Swarm mcpmemorymulti-agentsandboxtypescript | 980 | complex | ✅ | Self-hosted multi-agent orchestration service: a lead agent delegates queued tasks to Claude Code, Codex, and other workers in isolated containers. The **harness** contribution is the lead-to-worker hierarchy, the task queue, shared memory, and review gates, with MCP tools and Slack and GitHub integrations; the workers own their inner loops. |
| 19 | fractal python | 789 | slightly complex | ✅ | Hierarchical coding-agent **harness**: each autonomous loop works in its own git worktree and can delegate separable subtasks to child loops, so the execution tree grows recursively, with five coding-agent CLIs wired into per-node loops, shared SQLite run state, operator controls, and depth, cost, and time limits. |
| 20 | Claudexor multi-agentsandboxidetypescript | 520 | slightly complex | ✅ | Local-first control plane that routes one coding thread across Claude Code, Codex, Cursor, and OpenCode. The **harness** contribution is the layer around those agents: quota-aware rotation across isolated subscription profiles, bounded context handoffs between agents and accounts, best-of-N races, cross-family review, and typed apply gates. |
| 21 | AgentRL trainingpython | 364 | complex | ✅ | Multitask, multiturn RL for LLM agents; Ray-based scaling, rollout/actor workers—for teams that want to train agents, not just run them. |
| 22 | GraphCode memoryworkflowcli | 149 | slightly complex | ⚠️ FSL-1.1-MIT | macOS canvas that runs Claude Code, Codex CLI, Copilot CLI, and OpenCode sessions as nodes on a graph. The **harness** is the graph itself: each loop is typed by what ends it (a turn, a shell predicate or declared goal, a cadence, or a sub-graph), hand-off and spawn edges fire when a loop resolves, and a launchd daemon keeps sessions alive across app quits and reboots; the agent CLIs own their inner loops. |
| 23 | Agent Barn python | 110 | complex | ✅ | Control plane for teams of agents on your own Kubernetes cluster, deployed with Helm. The **harness** contribution is the layer around runtimes such as Hermes and OpenClaw: chat front ends (Slack, Teams, Telegram, Discord, email), tool wiring to Jira, GitHub, and Confluence, a model key per agent, and an audit record of every conversation, tool call, and cost. |