Multi-agent orchestration
coordinating teams, crews and swarms of agents
affaan-m/ECC affaan-m/ECC is the clear leader—it's a harness-native, cross‑harness agent OS focused on local execution, bundled skills, state/memory and production hardening. Before choosing, pick the single trade‑off you care most about (local privacy and auditability, research reproducibility, developer/IDE ergonomics, or a domain‑specific pipeline) because no one project optimizes all of them.
Which one matches your setup?
Answer any of the questions — the shortlist updates as you go. Recommendations come from the capability passports below, nothing else.
Comparison matrix
Axes are extracted from each project's docs by our review pipeline; the maturity score is computed from stars, growth and commit activity — not an opinion. Click a column to sort.
| Runs in | Models | Context | Cost to run | |||||
|---|---|---|---|---|---|---|---|---|
⭐ 247.7k +3872/7d | PR botCLIIDECoding-agent plugin | BYOKOpenAIAnthropicGeminiOllama / local | Whole-repo analysis | Severity gating | ●●●●● | Fully local | ●●●●● | Free OSS; optional Pro GitHub App ($19/seat/mo) + your model/API costs |
⭐ 86.1k +759/7d | CLIWeb appPR bot | BYOKOpenAIAnthropicGemini | Whole-repo access | None mentioned | ●●●●● | Self-hostable | ●●●●● | Free to self-host; optional paid OpenHands Cloud/Enterprise |
⭐ 81.3k +299/7d | CLIWeb appCoding-agent plugin | BYOKOpenAIAnthropicGeminiOllama / localFixed provider | Diff + related | Basic filters | ●●●●● | Self-hostable | ●●●●● | Your API key or self-hosted |
⭐ 70.4k +818/7d | PR botGitHub ActionCICLICoding-agent pluginWeb app | BYOKOpenAIAnthropicGeminiOllama / local | Whole-repo analysis | Severity gating | ●●●●● | Fully local possible | ●●●●● | Your API key for cloud models; self-hostable option |
⭐ 61.4k +5679/7d | CLIIDE | BYOKOpenAIAnthropic | Whole-repo analysis | Manual review & basic filters | ●●●●● | Can run fully local | ●●●●● | Use your agent subscriptions / API keys |
⭐ 58.1k +351/7d | CLICoding-agent pluginIDEWeb app | BYOKOpenAI | Project files & configs | Basic guardrails | ●●●●● | Self-hostable | ●●●●● | Requires your LLM API key (provider charges may apply) |
⭐ 56.1k +3211/7d | CLIWeb appIDECoding-agent plugin | BYOKOllama / local | Whole-repo analysis | Approval gates & checks | ●●●●● | Fully local capable | ●●●●● | Free local tools; optional paid provider API keys |
⭐ 48.8k +742/7d | Web appCLI | Fixed provider | Repo + related files | None mentioned | ●●●●● | Runs fully local | ●●●●● | Multica Cloud or self-host (no pricing specified) |
⭐ 42.2k +61/7d | Web appCLI | BYOKOpenAI | Diff only | Basic validation | ●●●●● | Cloud via your key | ●●●●● | Your API key (LLM usage) |
⭐ 39.0k +160/7d | CLICoding-agent pluginCI | BYOKAnthropicOpenAIGemini | Diff + related files | Staged verification | ●●●●● | Your API key | ●●●●● | Your API key(s), provider charges apply |
⭐ 29.2k +164/7d | CLIWeb app | OpenAIBYOK | Whole-repo analysis | Guardrails & human review | ●●●●● | Cloud APIs (your key) | ●●●●● | Your API key (or optional local models) |
⭐ 27.1k +90/7d | Web appCLI | BYOKOpenAIAnthropicGeminiOllama / local | Workspace access | No mechanisms | ●●●●● | Fully local | ●●●●● | Free, local compute; optional API keys |
Capability profiles
Six axes, 0–5 each. The shape tells you the strategy: a wide hexagon is a generalist, a spike is a specialist. Showing the 8 most established — the rest are in the full catalog.
A harness-native, cross-harness agent operating system that bundles skills, session/state memory, verification loops, and AgentShield for production multi-harness workflows.
A backend-agnostic, self-hosted developer control center that lets you run and switch between local, remote, and cloud agent backends without reworking your workflows.
Orchestrates long-horizon, multi-agent research workflows with sandboxed file-system sandboxes, subagents, memory and replay tools for reproducible deep-research tasks.
A production-ready agent meta-harness that orchestrates self-learning multi-agent swarms with zero-trust federation, a plugin marketplace, and self-hostable local-model support.
Runs any CLI coding agent side-by-side in isolated git worktrees (including remote SSH worktrees) with a desktop app and mobile companion for steering and comparison.
Combines autonomous role-based Crews with event-driven Flows in a single, production-ready framework for multi-agent orchestration.
Agentic end-to-end video production that can source, edit, and render real motion footage (not just animate still images).
Provides a managed, vendor-neutral platform that treats agents as assignable teammates with squad routing, reusable skills, and unified runtimes (local or cloud).
All repositories (129)
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first dev…
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes…
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, a…
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription.…
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewA…
World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent sk…
Make humans and AI agents work as one team — open-source and self-hostable.
OpenHuman is an open source personal AI for Mac, Windows and Linux — local-first memory, agent orchestration,…
Teams-first Multi-agent orchestration for Claude Code
Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Custom…
A lightweight, powerful framework for multi-agent workflows
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web,…
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-a…
Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Pyt…
ValueCell is a community-driven, multi-agent platform for financial applications.
Agent IDE that enables you to manage fleets of coding agents. It comes with an agentic orchestrator that plans…
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, an…
Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orche…
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordi…
可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Self-hosted knowledge agent platform for RAG, knowledge g…
IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents fo…
A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run…
Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop…
Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402…
Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.
Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and you…
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action…
A persistent workspace for development work that self-improves and continues beyond one session.
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode,…
Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.
Sprix AI at 屿智同行 — state-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks.
Source control for agents. Use multiple coding agents, track their changes and query them in one place
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and pen…
agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.
VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”…
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that kee…
An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies usi…
Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each oth…
Open-source Grok Bot alternative. Choose your own model and sandbox.
🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.
Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as dragga…
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Te…
Transform legacy systems into executable specifications for AI coding agents
AI video agents framework for next-gen video interactions and workflows.
One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own. 一句…
A smarter, self-hosted AI assistant — multi-user, multi-agent.
Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report…
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative executio…
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative executio…
Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and works…
An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework…
The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent j…
Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmu…
Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not wh…
The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust.
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with…
Govern, Observe, Direct - a real-time control room for agent societies
Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify…
An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, T…
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with gradin…
MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time…
Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.
♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex,…
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen…
Web UI for Pi Coding Agent that keeps sessions alive in real workspaces.
Control any coding agent on any device — from your phone.
Solo Agent — an open-source, local-first workspace where humans and AI coding agents collaborate through chann…
A local-first desktop workspace for running, organizing, and resuming multiple coding agents and shells with…
Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real…
Claude Code–style dynamic workflows for Pi: code-mode subagents with real model routing, journaled resume, git…
Terminal-first, open-source AI agent manager for any CLI agent (agent agnostic), any OS (mac, windows, linux).…
Hunter Community Edition · 私人金融 AI 团队 · AI 智能体 + AI 量化 · 开源自托管 · powered by opencode + Claude Code + MCP + mul…
SAW — SAFe Agentic Workflow AI Agent Harness for Multi-Agent Team Workflows Built on SAFe methodology (Scaled…
DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, m…
Open-source control plane for AI coding agents. Run an AI engineering team: parallel Claude Code, Codex, and G…
autonomous systems engineering cli agent for any cloud environment: AWS, GCP, Cloudflare, etc
Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps,…
Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with me…
Tessera — a workspace for organizing AI coding sessions across projects, collections, tabs, panes, and Git wor…
The open-source AI coworker for your team: agents with their own cloud computer, your tools and context, handi…
Cezar is a parallel coding agents orchestrator. Type a task, pick a workflow and an agent — Claude Code, Code…
A dashboard for running and coordinating multiple AI CLI agents at once.
FreeBuddy: desktop chat workspace for local CLI agents (codex / claude / opencode)
Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG…
一个生产级的深度研究 Agent 系统，从零构建多智能体编排、Red-Blue 对抗降噪、 语义级上下文压缩、跨 Agent 共享记忆四大核心能力，配套 165 次独立实验 + Bootstrap 统计显著性检验的完整评…
Local merge queue for parallel Claude Code agents
Advanced AI Code Strategy Advisor for Developer Agents (2026)
A local-first AI workspace — multi-provider chat, an autonomous coding agent, 3D models, ERPs, and multi-agent…
An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You…
Multi-CLI agent swarm orchestrated by Claude Code: external AI CLIs code in isolated worktrees, Claude verifie…
支持对接内部系统的 AI 排障工作台：通过 HTTP API / Webhook 接入工单与告警系统，串联代码、日志、配置和 Agent，并提供面向产品、运营、客服的 Web 自助分析页面。
MCP message broker + web dashboard for inter-agent communication. Let AI CLI agents (Claude Code, Gemini CLI,…
Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-nat…
Reina 桌面 AI Agent 发行仓库（仅安装包） | Release distribution for the Reina desktop AI agent — installers only. Windows…
OctoOffice - AI Agent Company Simulation. Command your CLI agent empire from the CEO desk.
Hosted alternatives
If running your own reviewer is more ops than you want, these managed services cover the same job.
The managed side of crewAI: deploy your crews to CrewAI's cloud and get a control plane on top — traces, a visual studio, scheduling and access control instead of hosting the runtime yourself.
Try CrewAI Enterprise →LangChain's hosting for LangGraph agents. It runs the graph for you with persistence, streaming and a debugging studio, so you ship the same orchestration code without standing up the server and state store.
Try LangGraph Platform →Microsoft's managed runtime for multi-agent systems, the hosted counterpart to AutoGen and Agent Framework. It handles orchestration, tool wiring and identity on Azure rather than on infrastructure you run.
Try Azure AI Foundry Agent Service →