Orchestrators & Multi-Agent

Workflow automation with AI agent capabilities and 400+ integrations. ~60K+ ⭐

An effortless way to experiment and prototype LangChain flows with drag-and-drop components and a chat interface

by Anthropic PBC - The official Anthropic implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code

GitHub's open-source toolkit for spec-driven development: spec.md → plan.md → tasks.md artifacts convert natural-language intent into a machine-checkable plan before any code is written, with /specify, /plan, /tasks, and /implement commands that run across Claude Code, Copilot, Codex, and Gemini CLI. The clearest reference implementation of treating spec/plan/task documents — not the prompt — as t

The AI orchestrator for running Codex, Claude Code, OpenCode, and Pi side-by-side in isolated git worktrees. It turns fleet-of-agents execution into a polished desktop IDE with a mobile companion, making parallel agent harness design accessible beyond shell-scripting teams

Self-hosted platform where agents wake on heartbeats to claim tickets, governed by org charts, budgets, and approval gates.

Adapts autoresearch for free T4 GPUs (Google Colab / Kaggle) with zero cost and zero local setup. Key changes: Flash Attention 3 → PyTorch SDPA, removes H100-only kernel dependency

Intelligent routing across multiple LLM providers with load balancing, intelligent fallbacks, rate limiting, and response caching. Achieves 40–60% token cost reduction through smart model routing (cheap models for simple tasks, capable models for complex reasoning). Essential infrastructure for harnesses operating under strict cost budgets where model selection is a per-turn decision

Agent orchestration platform -- deploy multi-agent swarms, coordinate autonomous workflows, distributed swarm intelligence, RAG integration

MetaGPT is a multi-agent framework enabling GPT to collaborate within a software company, facilitating complex tasks by assigning different roles to GPTs github | github profile

Unified proxy and SDK that routes to 100+ LLM providers behind a single OpenAI-compatible interface, with a Router handling retry/fallback across deployments, per-project cost and rate-limit tracking, and OTEL callback integrations. The right infrastructure layer when your harness needs provider resilience (automatic failover on 429/500 errors), budget guardrails, or the ability to swap models wit

No fortress, purely open ground. OpenManus is Coming

Managed agents platform where you assign tasks, track progress, and let agents compound skills between runs.

Background runtime that owns your agents' terminals: sessions survive reboot and reattach from any terminal or SSH, panes are marked working/blocked/idle, and agents themselves spawn panes and prompt each other over a CLI and socket API. One Rust binary.

Cross-harness plugin marketplace that maintains one source-of-truth plugins/ directory and generates harness-native artifacts for Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot. It is the clearest practical example of treating reusable agent capabilities as a portable distribution format rather than ad-hoc prompt files

Claude Code plugin that externalizes multi-agent orchestration as installable skills and staged team pipelines, with cross-provider advisor routing and built-in requirement-clarification interviews. The most widely adopted example of turning a single-agent CLI into a team-ready meta-harness without rewriting the underlying loop

"Vibe-Trading: Your Personal Trading Agent"

Agents are first-class members of shared channels on a Nostr relay you own, with their own keys and audit trails. Claude Code, Codex, Goose.

ChatDev is a virtual software company utilizing intelligent agents to revolutionize the digital world through programming, offering a highly customizable framework and integrating innovative approaches like Experiential Co-Learning, Docker support, Git management, and Human-Agent Interaction github | github profile

Task management for AI-driven development: PRD parsing, task expansion, multi-provider support and selective tool loading to save context

OpenAI's orchestration layer for moving from supervising coding agents to managing work: it monitors an issue tracker, creates isolated per-issue workspaces, and surfaces proof-of-work artifacts (CI status, review feedback, walkthrough videos) as the handoff signal. The spec deliberately leaves sandbox and approval policies implementation-defined so teams can match trust posture to environment, an

The leading TypeScript toolkit for building AI agents (20M+ monthly downloads, 25+ provider integrations). AI SDK 6 introduced a first-class Agent abstraction with ToolLoopAgent for production-ready tool execution loops, DevTools for local debugging, full MCP support, and type-safe UI streaming. The unified API across OpenAI, Anthropic, Google, and AWS Bedrock makes it the default choice for TypeS

OSS Zapier alternative with AI

50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.

Durable execution for long-running agent workflows

Harness builder for deterministic AI coding workflows, combining agent steps with scripts, validation gates, approvals, and isolated git worktrees. Claude Code, Codex, and more.

Self-hosted daemon running agents in parallel on your own machines, driven from desktop, iOS/Android, web, or CLI, with voice control, diff review, and no telemetry or forced log-ins. Claude Code, Codex, Copilot, OpenCode, Pi.

🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具，覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计）。搭配编排器 agency-orchestrator，一句话即可让多位专家按 DAG 自动协作。

Scales to 20-30 agents with a coordinator, git-backed issue tracking, health watchdogs, and a Bors-style merge queue.

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

(15.5k ⭐) - Bridge for connecting local AI coding agents to Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work, and other messaging platforms

Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex

Replaces the bloated CLAUDE.md pattern with a progressive spec system: agents load only the standards, task PRDs, and session journals relevant to the current step. The cross-platform adapter layer turns vendor-specific harness configuration into a portable team practice rather than a per-tool hack

Desktop workspace that runs and supervises teams of coding agents from planning to merge: project-aware orchestration splits work into workers with isolated workspaces, tracked on a live Kanban with PRs, CI, and review, plus iPhone and Android apps. Claude Code, Codex, and 30+ harnesses.

(12.4k ⭐) - A comprehensive collection of specialized AI agents designed to accelerate and enhance every aspect of rapid development

Practical design system for agent loops with seven production patterns, cross-tool starter kits, and CLI tools that score readiness, scaffold state, estimate cost, detect drift, and isolate worktrees. The clearest open-source resource for moving from one-off prompting to durable, observable agent loops

Ekko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.

https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成

The Open Runtime for AI Agents

Databricks' open-source meta-harness (June 2026) that sits above Claude Code, Codex, Pi, and custom agents to compose, govern, and share live agent sessions from one control plane. The key harness insight is that enterprises don't need another agent framework — they need a portability and governance layer above the agents they already run, with policy-driven sandboxing and cost caps enforced outsi

Agentic AI Framework for Java Developers

Autonomous novel-writing CLI agent that orchestrates 10 specialized agents with 33-dimension continuity auditing, anti-AI-slop filtering, and style cloning for long-form fiction

A UI-Focused Agent for Windows OS Interaction

Bindu: The identity, communication, and payments layer for AI agents.

by backnotprop - Interactive review UI that intercepts ExitPlanMode via hooks, letting you visually annotate plans with comments, deletions, and replacements before approving or denying with detailed feedback. Has since grown to cover code and diff review, PRs, and rendered HTML artifacts, with feedback sent straight back to the agent. Supports several coding agents alongside Claude Code

by Anthropic - The official GitHub Action for running Claude Code in CI: mention @claude in issues and pull requests to delegate code changes, reviews, and fixes

by Frank Bria - An autonomous AI development framework that enables Claude Code to work iteratively on projects until completion. Features intelligent exit detection, rate limiting, circuit breaker patterns, and comprehensive safety guardrails to prevent infinite loops and API overuse. Built with Bash, integrated with tmux for live monitoring, and includes 75+ comprehensive tests

by revfactory - A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use. Resources are in Korean but can produce high-quality English-language output

(7.7k ⭐) - Local multi-agent harness that works with existing Claude Code and Codex subscriptions to run an office of agents

TypeScript-native orchestration for sandboxed coding agents that treats provider-agnostic isolation (Docker, Podman, or Vercel Firecracker microVMs) as a primitive, not a framework. The built-in review-pipeline and parallel-AFK-agent patterns demonstrate how lightweight harness layers can enforce safety without the complexity of full graph orchestration

by smtg-ai - A terminal app that manages multiple Claude Code, Codex, and other local agents (including Aider) in separate workspaces, allowing you to work on multiple tasks simultaneously

为OPC/中小微企业量身打造的自媒体获客智能体

Astro's TypeScript-native agent harness that treats an agent as a function composed of model, sandbox, skills, tools, and MCP servers. The deploy-anywhere runtime (Node, Cloudflare Workers, GitHub Actions, Daytona) and first-class durability make it a practical reference for building autonomous agents rather than chatbots

by Mike Schwarz - Combines Claude Code, Codex, and Pi terminal sessions into persistent long-running teams. Agents message each other directly over tmux and queue work to each other, instead of the user relaying messages. Teams and agents are saved as YAML files, and a running team can be snapshotted and restored later

Coordinates coding agents, source control, CI, review, approvals and feedback to turn routine backlog issues into review-ready pull requests. Supports Claude, Cursor and OpenAI.

by Ran Aroussi - Really comprehensive and feature-packed project-management workflow for Claude Code. Numerous specialized agents, slash-commands, and strong documentation

pi extension plus dashboard for persistent experiment loops, live metrics, confidence tracking, and resumable autoresearch sessions

ShortGPT is an AI-powered framework for automating content creation, including video editing, voiceover synthesis, caption generation, and asset sourcing, with support for multiple languages and seamless integration with Google Colab and Docker for easy deployment github | github profile

Local-first desktop workspace for AI coding agents with persistent projects and sessions, model switching, Plan/Goal modes, permission controls, plugins, MCP, and multi-agent orchestration

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。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.

(7.1k ⭐) - A specialized Claude Code workspace for creating long-form, SEO-optimized blog content for any business

A pixel office for your OpenClaw: turn invisible work states into a cozy little space with characters, daily notes, and guest agents. Code under MIT; art assets for non-commercial learning only.

GEPA (Genetic-Pareto) — ICLR 2026 Oral. Reflective prompt evolution that outperforms RL (GRPO) on benchmarks. Optimizes any textual parameters against any metric using natural language reflection

Local-first multi-agent desktop application where a Commander coordinates specialist agents for research, coding, data analysis, documents, and media; MIT-licensed with bring-your-own model keys

Token-efficient microkernel agent with an on-device SquillaRouter that dispatches each turn to the cheapest capable model, a unified turn loop across CLI/Web/chat, and persistent memory with on-device embeddings. Demonstrates that harness-level routing and loop optimization — not just model scale — are the binding levers for intelligence density

The Open Source Agentic IDE. Create and orchestrate coding agents, show app previews and run git workflows. Use your favorite models across all providers.

Claude Code skill that generalizes autoresearch into a reusable loop for software, docs, security, shipping, debugging, and other measurable goals

Provider-neutral control plane that sits above existing harnesses (Codex, Claude Code, Cursor) and keeps long-horizon objectives, gates, todos, evidence, and quota stable across bounded agent turns. The local-first state kernel makes multi-day work reviewable, restartable, and handoff-safe without replacing the runtime underneath

The definitive collection. 136+ agents across 10 categories (core dev, language specialists, infra, security, data/AI, DX, domains, business, meta, orchestration). Just clone and use

Self-hosted orchestration dashboard for agent task dispatch, multi-agent workflow coordination, and spend monitoring across gateways. The zero-external-dependency design (SQLite, single pnpm start) makes it the most practical open-source control plane for teams that need governance and cost visibility without building infrastructure from scratch

Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.

Production-ready Java framework for distributed, enterprise-grade agents with workspace sandboxing, permission-gated tool calls, AOP-style middleware, and cross-replica session recovery. The Java complement to AgentScope Runtime for teams that need a typed, JVM-native harness stack

Code-first task decomposition framework with a planner/executor split and a plugin system for injecting domain knowledge into the planning layer. The most complete reference implementation of plan-then-execute with stateful task tracking

DevOpsGPT is an AI-driven software development automation solution that combines large language models with DevOps tools to convert natural language requirements into working software, enhancing development efficiency, shortening cycles, and reducing communication costs github | github profile

Host agent that plans a complex task as a DAG and coordinates dependencies and parallel execution across built-in research, coding, design, and on-call agents and third-party agents over ACP, CLI, or OpenAI-compatible APIs. Presets include Claude Code, Codex, OpenCode, OpenClaw, Hermes Agent, GitHub Copilot, Qwen Code, and Kimi Code.

Vercel's filesystem-first framework for durable AI agents: instructions, typed tools, on-demand skills, message channels, and cron schedules live in conventional directories, making the harness inspectable and version-controlled by default. A concrete reference for treating the project filesystem as the agent authoring interface rather than burying configuration in framework internals

Next-generation personal AI assistant powered by LLM, RAG and agent loops. Supports computer-use, browser-use, coding agent, 30+ model providers, visual workflow builder, and MCP tools. Self-hostable with admin dashboard

AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).

AI-Driven Development Life Cycle workflow rules for coding agents. Supports Kiro, Q Developer, Cursor, Cline, Claude Code

(5.6k ⭐) - Best UI for Claude Code with local and remote agent execution

Compiles agentic workflows written in Markdown into GitHub Actions YAML. Read-only by default, with writes only through sanitized safe-outputs. Copilot, Claude, Codex, Gemini.

Agent swarm intelligence for autoresearch — spawns parallel GPU research directions, distributes work across agents, aggregates results

Cross-platform local MCP capabilities for ChatGPT with Chrome integration, Goal, Compact & Resume, and durable multi-agent workflows.

Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

Platform for building and running AI agents across the full lifecycle — build, test, deploy, monitor, improve. Hosts your agents, runs their tools, and coordinates them over an event mesh, with sessions, artifacts, auth, evaluators, and observability built in.

A team of long-lived bots for DeepSeek Harness, with main bots, bot-to-bot messages and group chats.

(4.5k ⭐) - Multi-agent deliberation framework for comparing perspectives on difficult decisions across coding agents

Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems

(4.3k ⭐) - Supercharge Claude Code with a team of specialized AI agents that work together to build complete features, debug complex issues, and handle any technology stack with expert-level knowledge

Tauri/React/Rust desktop app for orchestrating multiple Codex agents across workspaces. Multi-workspace, Git integration, prompt library

Open-source platform for building AI agent networks with multi-protocol support (WebSocket, gRPC, HTTP, MCP, A2A) and multi-agent orchestration

Lets any OpenAI-compatible vision model operate a real iPhone, seeing it via AirPlay mirroring and tapping via an ESP32-S3 acting as a USB mouse and keyboard

(3k ⭐) - Turns Claude Code into a general-purpose AI offensive/defensive security agent

by Patrick Ellis - Three review workflows developed at an AI-native startup: automated PR code review (dual-loop, GitHub Actions plus slash command), security review against OWASP Top 10 with severity-classified findings, and the widely-copied design-review agent that drives Playwright MCP to check UI/UX and accessibility against a live preview. Each ships as a slash command, a subagent, and a wor

Where people and agents build in tune.

A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。

Multi-agent AI orchestration platform for automation, workflows, and developer tools. Golutra transforms Codex, Claude Code, and OpenClaw into a unified agent system with parallel execution, task orchestration, long-running workflows, and AI productivity workspace.

Self-hosted unified API for running Codex, Claude Code, DeepSeek Harness, Pi, and other terminal agents through the open Unified Harness Protocol (UHP), with sessions, streaming, file access, cancellation, and failure handling. Worth including because harness fragmentation is becoming a real operations problem — this is the clearest open-source attempt to make agent runtimes interchangeable behind

Connect any AI copilot or autonomous agent to your enterprise tools — through a single, secure MCP/Agent gateway with built-in identity, access control, and full observability.

by Michael Denyer - Claude Code version of Lauren Tan's Poteto's pstack. Rigorous agent workflows with Cursor primitives translated to other agents. Supports multiple providers