Orchestrators & Multi-Agent tools for Claude Code

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.

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

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

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.

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。

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

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

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

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

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

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

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

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

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

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

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

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.

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.

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

(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

(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

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

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

(3.1k ⭐) - A comprehensive collection of specialized AI subagents for Claude Code, designed to enhance development workflows with domain-specific expertise

(3.5k ⭐) - Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents

by Chachamaru - A Claude Code development harness that enables reliable high-quality development through an autonomous Plan -> Work -> Review cycle. Well documented and includes an Output Style

by mikeyobrien - Ralph Orchestrator implements the simple but effective "Ralph Wiggum" technique for autonomous task completion, continuously running an AI agent against a prompt file until the task is marked as complete or limits are reached. This implementation provides a robust, well-tested, and feature-complete orchestration system for AI-driven development. Also cited in the Anthropic Ralph p

An autonomous company working 24/7 on your own PC - Windows/Linux/macOS.

Bash script that loops Claude Code, Codex, OpenCode, Cursor, Qwen, or Droid until the task is done.

Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.

Battle-tested Claude Code workflows from power users. Self-correcting memory, parallel worktrees, wrap-up rituals, 8 hook types, 5 agents, and the 80/20 AI coding ratio. Install: /plugin marketplace add rohitg00/pro-workflow

(2.8k ⭐) - A background agent that whispers to Claude Code. A subconcious agent that watches your sessions, reads your files, builds up memory over time, and whispers guidance back

(2.7k ⭐) - Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark

Open-source operating system for AI agents — plug in the agent CLIs you already use and run them as a team on loops and schedules, with shared memory, permissions and approvals

(2,723 ⭐) - Multi-agent platform that gives each agent a dedicated computer with a desktop, browser, network, and long-term memory; supports hosted Claude Code and Codex agents

(2,747 ⭐) - Multi-agent development workflows with task routing across Claude Code, Codex, Gemini, and OpenCode, plus planning, review, and testing commands

Desktop app where you give high-level commands to autonomous coding-agent teams across Claude Code, Codex, OpenCode, Cursor, Grok, GitHub Copilot, Kiro, Z.AI, MiniMax, Kimi, 200+ models, and 75+ LLM providers. Agents coordinate through inter-agent messaging, Kanban tasks, and built-in code review.

Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition.

Ports Claude Code's full agent loop to DeepSeek V4 Pro and other Anthropic-compatible backends while preserving the same UX. The strongest practical evidence that loop architecture — not model identity — determines agent behavior, and a concrete starting point for building backend-agnostic harnesses

Drop-in multi-agent framework where protocol enforcement is a mechanical gate, not a prompt request: IDE-level hooks check every code-changing turn for required reviewers, memory updates, and supply-chain integrity before the turn can complete. Built on stdlib Python with zero dependencies, it demonstrates how to build deterministic harness constraints that even frontier models cannot override

Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity, Kimi, Augment Code, Qwen, fully end-to-end encrypted

(2,063 ⭐) - Coding-agent workflow engine with configurable independent reviews, repair loops, review gates, and retry limits across Claude Code, Codex, Pi, and Copilot

Google's experimental "hypervisor for agents" (April 2026, Apache-2.0): orchestrates Claude Code, Gemini CLI, Codex, and OpenCode as isolated concurrent processes, each with its own container, git worktree, credentials, and network policy. The core harness insight is *isolation over coordination* — let agents run fully autonomous inside their containers and enforce guardrails at the infrastructure

(2.1k ⭐) - Custom subagents to use with Claude Code

by Prasad Chalasani - Well-crafted toolset for session continuity, featuring skills/commands to avoid compaction and recover context across sessions with cross-agent handoff between Claude Code and Codex CLI. Includes a fast Rust/Tantivy-powered full-text session search (TUI for humans, skill/CLI for agents), tmux-cli skill + command for interacting with scripts and CLI agents, and safety hooks to

(1.8k ⭐) - Open-source AI assistant framework with skills and agent workflows

Long-horizon computer-use harness that runs on top of Claude Code and Codex, splitting work into Manager, Executor, and Auditor roles so only independently verified results enter persistent task state. The clearest August 2026 open-source reference for carrying desktop-and-CLI tasks through dozens of hours without state drift

(1.4k ⭐) - Continuous background code review database for agents, work faster and smarter with accountability for every line of generated code

(974 ⭐) - Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work

(1.6k ⭐) - Collection of specialized AI subagents for Claude Code for personal use

(946 ⭐) - Claude Code workspace where AI advisors debate business decisions, with a local visual discussion room, scored verdicts, and PDF reports

Herdr mobile client for iPhone and Android. A self-hosted PWA to drive Claude Code, Pi, Codex and OpenCode in Herdr, tmux or zellij from your phone. Push alerts, no app store.

Executes an implementation plan autonomously with a fresh session per task, plus validation, retries, multi-phase review, and automatic commits. Claude Code, Codex.

Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions.

Shared rooms where people and agents collaborate: local coding agents get persistent identities with handles, inboxes, and memberships, while agents keep running on your own machine.

Local-first AI agent office simulator. Orchestrates CLI, OAuth, and API-connected agents as a virtual autonomous company

Shogun to karo to ashigaru hierarchy running up to 10 agents over tmux with no coordination API cost.

The open-source collaboration system for people and AI agents. Share context, coordinate tasks, and work in parallel with your team, cloud agents, Codex, Claude Code, Grok, Grok Bot, OpenCode, Antigravity, and Cursor.

(1.3k ⭐) - A curated list of awesome Claude Code Sub-Agents

Deterministic scheduler for 40+ CLI coding agents running in parallel git worktrees with an HMAC-signed audit chain, signed agent cards, and per-artefact lineage. The zero-LLM coordination loop and tamper-evident audit trail make it the only open-source orchestrator designed for compliance-sensitive agent fleets

Recursive self-improving harness that runs multi-generation evaluation loops, distilling successful strategies into persistent playbooks and trace datasets that future agents inherit. The five-role architecture (competitor, analyst, coach, architect, curator) and built-in production trace capture make it the most complete open-source reference for turning meta-harness optimization into a deployabl

Automated skill discovery for coding agents: evolves reusable skills and prompts from failed trajectories against benchmarks, with support for Claude Code, Codex CLI, OpenCode, OpenHands, and Goose

Shopify's open-source Ruby DSL for structured AI workflows that interleaves deterministic steps (shell commands, Ruby code) with agentic steps via Claude Code or Pi. Its "non-determinism is the enemy of reliability" philosophy makes it a concrete reference for building reproducible, version-controlled harnesses where guardrails are structural rather than prompt-level

Native-Rust agent harness platform with four surfaces (GUI, CLI, web, one-shot), multi-provider routing, and sovereign-by-design architecture. The most complete open-source reference for a locally-run, offline-capable harness that unifies MCP, skills, AGENTS.md, hooks, and session resumption in a single binary

When Claude keeps giving you bad answers, make 100 versions of it fight to the death. Same task, 100 different strategies, a bracket, one answer left. Free Claude Code skill.

Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.

(1.1k ⭐) - A collection of open-source skills for AI coding agents (Claude Code, OpenClaw, etc.) powered by the Pika Developer API

Universal agent orchestrator. Route tasks between Codex, Claude Code, and Gemini CLI based on model strengths

Terminal UI companion for CLI-based coding agents (Claude Code, Cursor, Gemini) with unified conversation history, git integration, task management, and workspace control

Local, Apache-2.0 layer that lets Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one machine work as one team: shared memory and a file-based mailbox, handing a task to another agent with context intact when one hits its usage limit, and reviewing each other's work

by Clayton Farr - A remarkably detailed and comprehensive guide to the Ralph Wiggum technique, featuring well-written theoretical commentary paired with practical guidelines and advice

(928 ⭐) - A comprehensive collection of 100+ production-ready development subagents for Claude Code

by avifenesh - Workflow automation system for Claude with a group of useful plugins, agents, and skills. Automates task-to-production workflows, PR management, code cleanup, performance investigation, drift detection, and multi-agent code review. Includes agnix for linting agent configurations. Built on thousands of lines of code with thousands of tests. Uses deterministic detection (regex, AST) w

(974 ⭐) - Delegate tasks to Codex GPT 5.2 directly from within Claude Code

Mission control for your AI agents

Self-hosted AI company operating system where a lead agent delegates goals to workers in isolated containers, with persistent memory, schedules, and review gates. Claude Code, Codex, pi, OpenCode, Cursor, Amp, Grok, Devin, and ACP agents.

by Martin Joly - A curated list of resources about Ralph, the AI coding technique that runs AI coding agents in automated loops until specifications are fulfilled

(607 ⭐) - An agent orchestration harness for Claude Code. It coordinates multiple AI agents in parallel, persists memory across sessions, and routes your intent to the cheapest execution path automatically

(841 ⭐) - A powerful orchestration framework that runs multiple Claude Code (cc) sessions in parallel to systematically improve your codebase

Self-hosted, open-source AI browser agent that browses, clicks, types and reads real web pages from plain-English instructions; runs locally on a patched Firefox engine and ships as an MCP server and a local web UI