Skip to content
/
§ a6

Multi-agent orchestrator

Spawns N agents in parallel or hierarchical patterns. Worktrees, swarms, queens+workers.

44 primary frameworks · 64 lower-confidence entries

Hermes Agent (NousResearch)
hermes-agent
★ 168k
Tier A

Self-improving personal AI agent with closed learning loop, 7 terminal backends, and messaging gateway — not tied to any AI coding tool.

OpenCode
opencode
★ 165k
Tier A

Terminal-first AI coding agent with multi-model routing, native desktop app, and a typed .opencode/ configuration system for agents, commands, skills, and…

OpenHands
openhands
★ 75k
Tier A

Open-source AI software development platform (open-source Devin alternative) with Docker sandbox isolation, 77.6% SWE-bench score, and 25+ trigger-activated…

DeerFlow
deerflow
★ 70k
Tier A

Long-horizon superagent that researches, codes, and creates by orchestrating parallel sub-agents with isolated contexts in Docker sandboxes, driven by…

oh-my-openagent (omo)
oh-my-openagent
★ 60k
Tier A

Multi-provider AI agent orchestration for OpenCode: escape vendor lock-in by routing Sisyphus (Claude/Kimi/GLM) and Hephaestus (GPT-5.5) as a coordinated team.

Claude-Flow / Ruflo
claude-flow
★ 55k
Seed

Eliminates single-agent context limits and sequential bottlenecks by orchestrating fault-tolerant swarms of specialized AI agents with shared persistent memory.

gpt-engineer
gpt-engineer
★ 55k
Tier A

ARCHIVED — the original LLM-driven code generation experiment that generates entire applications from a prose specification file.

Aider
aider
★ 45k
Tier A

Terminal-native AI pair programming with git-first edit semantics and automatic commit messages.

Continue
continue
★ 33k
Tier A

AI code review as source-controlled, enforceable CI checks — green/red GitHub status checks powered by markdown-defined agent instructions.

oh-my-codex (Yeachan-Heo)
oh-my-codex-yeachan
★ 30k
Tier A

Add structured planning, durable state, and multi-agent team coordination to OpenAI Codex CLI without replacing it.

VoltAgent awesome-claude-code-subagents
voltagent-subagents
★ 21k
Tier A

154+ domain-specialized Claude Code subagents across 10 categories, installable as plugins with no commands, skills, or hooks — pure agent catalog.

Codex Plugin for Claude Code (openai)
codex-plugin-cc
★ 20k
Tier A

Use OpenAI Codex as a reviewer and task executor from inside an active Claude Code session without leaving the CC workflow.

SWE-agent
swe-agent
★ 19k
Tier A

Research-grade GitHub issue fixing agent with YAML-configurable prompts, one-command-at-a-time REPL loop, and batch evaluation support for SWE-bench…

Gas Town
gas-town
★ 16k
Tier A

Coordinate 20-30 concurrent AI coding agents on shared repos with persistent work state, crash recovery, and autonomous health monitoring.

claude-code-spec-workflow (Pimzino)
claude-code-spec-workflow
★ 3.7k
Tier A

Two-workflow Claude Code spec harness: structured feature development plus dedicated bug-fix pipeline, with a real-time dashboard and Tauri desktop app for…

jeremylongshore/claude-code-plugins-plus-skills (Tons of Skills)
jeremylongshore-plugins-skills
★ 2.2k
Tier A

431 plugins, 2,810 skills, 200 agents with a dedicated npm CLI (ccpi) and marketplace website — the Claude Code plugin ecosystem treated as a commercial…

Claude Command Suite (qdhenry)
claude-command-suite-qdhenry
★ 1.3k
Tier A

216+ slash commands across 26 domain namespaces + 12 skills + 54 agents covering full-stack development, DevOps, security, media processing, browser AI, and…

Chorus
chorus
★ 915
Tier A

Full-stack agent harness with Reversed Conversation philosophy — AI proposes, humans verify — enforced via a permission-gated MCP server and production web UI

Cursor Rules Pack v2
cursor-rules-pack-v2
★ 853
Tier A

Official Cursor plugin marketplace providing CI workflows, engineering principles, parallel cloud-agent orchestration, transcript-based memory, and iterative…

your-claude-engineer (coleam00)
coleam00-your-claude-engineer
★ 850
Tier A

Autonomous software factory that takes a plain-text app spec and delivers a running web app with Linear issues tracked, GitHub PRs created, and Slack…

Roo Commander (jezweb)
roo-commander
★ 725
Tier A

Bridge Claude Code's 60+ production-tested skills to Roo Code via an orchestrator mode and CLI skill-discovery tool.

adversarial-spec
adversarial-spec
★ 546
Tier A

Iteratively refines product specifications through multi-LLM adversarial debate until all models reach consensus, surfacing gaps and edge cases that any single…

Smart Ralph
smart-ralph
★ 339
Tier A

Turn a vague feature idea into structured specs and then execute them task-by-task with fresh subagent context, without losing state across sessions.

Symphony (sincover)
symphony-sincover
★ 260
Tier A

12-role musical-metaphor hierarchy (Composer→Score→Conductor→Performer) for Roo Code, with three automation levels, Mermaid visualization, and append-only…

spec-kit-command-cursor (madebyaris)
spec-kit-command-cursor
★ 182
Tier A

Cursor-native SDD toolkit with async background subagent trees, parallel DAG execution with file-conflict detection, checkpoint-resume, and downstream spec…

Claude Swarm (affaan-m)
claude-swarm
★ 172
Tier A

Decompose complex tasks via Opus into a dependency DAG, execute waves of Haiku workers in parallel, then Opus quality-gates the combined output — mirroring…

Spec-Driven Agentic Development
spec-driven-agentic-development
★ 172
Tier A

Generates EARS-formatted specs via parallel codebase exploration agents before any implementation begins, ensuring specs reflect actual code patterns.

OpenCode Orchestrator
opencode-orchestrator
★ 167
Tier A

Hub-and-spoke hierarchical orchestration for OpenCode with Chase-Lev work-stealing, MVCC state sync, and evidence-based anti-hallucination mandates.

Code Conductor (ryanmac)
code-conductor
★ 101
Tier A

Decentralized swarm orchestration for parallel Claude Code agents using GitHub Issues as the atomic task queue and git worktrees for zero-conflict isolation.

revfactory Claude Code Harness (A/B Research)
revfactory-cc-harness
★ 98
Tier A

Empirically proves that Claude Code pre-configuration improves output quality by 60% across 15 software engineering tasks.

oh-my-codex (scalarian)
oh-my-codex-scalarian
★ 65
Tier A

A focused Codex-only workflow runtime with tmux team execution, MCP servers, and durable .omx/ state — the v2 vision without Claude bridge.

barkain/claude-code-workflow-orchestration
barkain-workflow-orch
★ 60
Tier A

Enforce Director/Coder split via adaptive hook-based delegation nudges, native plan mode as the handoff boundary, and 8 specialized agents for domain execution.

Claude Conductor (rbarcante)
claude-conductor-rbarcante
★ 53
Tier A

Context-Driven Development plugin that enforces a spec-plan-implement lifecycle with Python-CLI context management, pattern library, and ADR logging for Claude…

aistack
aistack
★ 51
Tier A

Coordinates 11 specialized AI agents with adversarial code review, JWT agent identity, and 6-provider multi-model routing against shared SQLite memory.

ovachiever/droid-tings
droid-tings
★ 44
Tier A

375 aggregated skills + 155 droids from 15+ repos covering AI/ML, scientific research, and development — targeting both Claude Code and Factory's Droid system.

cc-plugin-codex (sendbird)
cc-plugin-codex-sendbird
★ 42
Tier A

Use Claude Code for review and rescue from inside a Codex session — the semantic inverse of codex-plugin-cc, with Codex as host and Claude as the worker.

GoopSpec
goopspec
★ 29
Tier A

Enforces spec-driven development in OpenCode via a 5-phase workflow with two mandatory human contract gates, a 16-agent multi-model orchestration system, and a…

do-it
do-it
★ 20
Tier A

Stop asking AI agents to remember process — install risk-routing, evidence-gated completion, and explicit subagent contracts as automatic hooks.

Claude Conductor (lackeyjb)
claude-conductor-lackeyjb
★ 14
Tier A

Simplified Context-Driven Development plugin with 3-agent specialization (planner/implementer/reviewer) and lifecycle hooks for passive context management.

oh-my-codex (sigridjineth)
oh-my-codex-sigridjineth
★ 14
Tier A

A personal Codex plugin extension adding tier-based model routing, LSP/AST tooling, and notification integrations to the canonical oh-my-codex workflow.

shinpr/codex-workflows
shinpr-codex-workflows
★ 12
Tier A

Codex-native 13-stage pipeline with context-isolated subagents that prevents assumption drift in large multi-file changes.

SuperSpec (danielhanold)
superspec
★ 8
Tier A

Eliminates the duplicate artifacts and manual skill selection overhead of using OpenSpec and Superpowers together by providing a schema that enforces their…

Claude Conductor (MZWASHERE)
claude-conductor-mzwashere
★ 0
Tier A

Exact copy of lackeyjb/claude-conductor with spam README; no independent value.

Stoneforge
stoneforge
Tier A

Three-role (Director/Worker/Steward) orchestration platform with dependency-aware dispatch daemon, automatic merge-via-Steward, and a full web dashboard…

Show 64 lower-confidence entriestier-b · tier-c · unknown · delta reports

These entries map to § a6 by tag but carry weaker evidence — fewer documented primitives, delta reports of absent skills, or marketing-only sites without a public repo. They're listed for completeness; treat them with appropriate caution.

pi-mono ★ 55k
pi-mono

Minimal, extensible TypeScript terminal coding agent with multi-provider LLM API, TUI library, and TypeScript Extension API — adapt to workflows without forking…

Ruflo (ruvnet) ★ 55k
ruflo
Agno ★ 40k
agno

Build, deploy, and manage production agent platforms with full ownership of data, memory, and compute.

Claude Code Templates (davila7) ★ 28k
claude-code-templates-davila

npm-installable marketplace of 600+ Claude Code agents, commands, hooks, MCPs, and settings for composable workflow assembly.

Ralph (snarktank) ★ 20k
ralph-snarktank

Run an AI coding tool in a fresh-context loop, one user story at a time, until all stories in prd.json pass.

PydanticAI ★ 17k
pydantic-ai

Bring FastAPI's ergonomics (typed dependency injection, Pydantic validation, IDE auto-completion) to Python agent development.

Aperant ★ 14k
aperant

Cross-platform Electron desktop for autonomous multi-agent coding with kanban UI, parallel git worktrees, self-validating QA loop, and GitHub/Linear integration…

Hive (aden-hive) ★ 10k
hive-aden

Auto-generate and execute self-healing multi-agent DAGs for complex business workflows from a natural language goal.

Ralph for Claude Code ★ 9.2k
ralph-claude-code

Production-grade Claude Code autonomous loop with dual-condition exit gate, rate limiting, circuit breaker, session management, and live monitoring.

VoltAgent ★ 9.2k
voltagent

TypeScript-native AI agent framework with typed contracts, composable guardrails, and a cloud ops console.

mcp-agent ★ 8.3k
mcp-agent-lastmile

Build durable, composable agents using MCP as the only protocol, implementing every pattern from Anthropic's Building Effective Agents paper.

Yao ★ 7.5k
yao

Run AI agents and full-stack web apps from a single Go binary with TypeScript hooks, container sandboxing, and GraphRAG — zero runtime dependencies.

ZCF — Zero-Config Code Flow ★ 6.0k
zcf

Zero-config one-command setup for Claude Code + BMAD methodology + API relay provider configuration.

Cloudflare Agents ★ 5.0k
cloudflare-agents

Build persistent, stateful AI agents backed by Cloudflare Durable Objects — scale to millions of instances, each hibernating at zero cost when idle.

HiClaw ★ 4.7k
hiclaw

Kubernetes-native multi-agent platform where Worker and Manager agents collaborate in a Matrix IM room with enterprise credential isolation via Higress AI gatew…

OpenAgentsControl (OAC) ★ 4.2k
openagentscontrol

AI agents generate code matching your team's patterns by loading project context before every execution.

TinyAGI ★ 3.6k
tinyagi

24/7 multi-agent multi-team platform with Discord/Telegram/WhatsApp channels, peer-to-peer message-passing coordination, and a Next.js web portal for one-person…

LangChain MCP Adapters ★ 3.5k
langchain-mcp-adapters

Bridge MCP tool protocol to LangChain/LangGraph BaseTool interface with zero boilerplate.

Docker Agent ★ 3.0k
docker-agent

Define multi-agent AI systems in YAML, package via OCI, and run with Docker — no code required.

Amazon Bedrock AgentCore Samples ★ 2.9k
agentcore-samples

Managed cloud infrastructure for deploying AI agents at production scale — eliminating undifferentiated heavy lifting of compute, memory, identity, and security…

Google Agents CLI ★ 2.6k
google-agents-cli

Google's official CLI and skill pack for building production ADK agents — enforcing scaffold-first, eval-driven development across Claude Code, Gemini CLI, Code…

Agent Deck ★ 2.5k
agent-deck

Terminal mission control for managing fleets of parallel AI coding agent sessions with fork, MCP, conductor, and worktree support.

NeMo Agent Toolkit ★ 2.3k
nemo-agent-toolkit

Add enterprise-grade instrumentation, profiling, evaluation, and RL fine-tuning to any AI agent framework without migrating your code.

MCP Agent Mail ★ 2.0k
mcp-agent-mail

Provides an asynchronous mail-like coordination bus (identities, inboxes, file leases, Git-auditable messages) so multiple coding agents can work the same codeb…

claude-codepro (Pilot Shell) ★ 1.7k
claude-codepro

Adds spec-driven planning, enforced TDD, persistent memory, multi-agent review, and a local web dashboard to Claude Code — making it production-grade for engine…

Tsumiki ★ 965
tsumiki

Japanese-developed Claude Code plugin delivering 40+ commands covering requirements (EARS) → design → TDD → implementation → verification for full project lifec…

Loki Mode ★ 944
loki-mode

Takes a spec (PRD/issue/OpenAPI) and autonomously produces a production-ready Git repository through RARV cycles, 11 blocking quality gates, and 41 specialized …

evo ★ 770
evo

Autonomously optimize code through parallel tree-search experiments with shared state, gate-validated results, and configurable frontier strategies.

power-bi-agentic-development ★ 619
power-bi-agentic-dev

Makes Claude Code a competent Power BI/Fabric developer by providing 25 domain skills, 8 validator agents, and PostToolUse hooks that enforce TMDL/PBIR/DAX form…

Clean-Coder-AI ★ 576
clean-coder-ai

Autonomous 2-in-1 AI developer + scrum master that plans an entire project as Todoist tasks and executes them task-by-task with a LangGraph multi-agent pipeline…

Subtask ★ 330
subtask-zippoxer

Gives a lead AI agent a Go CLI + git worktree infrastructure to dispatch parallel worker agents, track progress, and orchestrate merges without user involvement…

OpenASE ★ 243
openase

Turns tickets into working code via AI agents that autonomously claim tickets, execute versioned workflow harnesses, and pass lifecycle hook quality gates.

glebis/claude-skills ★ 225
glebis-skills

48-plugin personal productivity OS with flagship multi-agent TDD skill implementing information isolation between test-writing and implementation phases.

Gemini CLI Skill for Claude Code ★ 184
gemini-cli-skill-foray

Teaches Claude Code to delegate tasks to Gemini 3 Pro via CLI for second opinions, Google Search grounding, and codebase architecture analysis.

alexeykrol/claude-code-starter v6 ★ 180
alexeykrol-cc-starter

Russian-language Claude Code starter v6 with auto project-type detection, SNAPSHOT.md session state, pre/post compact hooks, and repo_access git-history control…

ContextKit ★ 169
contextkit

Spec-driven 4-phase planning workflow for iOS/macOS Swift development in Claude Code, with quality-specialized subagents for accessibility, localization, and mo…

oh-my-claude (TechDufus) ★ 147
techdufus-oh-my-claude

Adds three-reviewer quality gate chain (advisor+critic+risk-assessor) and Python-hook enforcement layer to Claude Code before execution.

Autospec ★ 130
autospec

Go CLI that orchestrates spec → plan → tasks → implement in fresh isolated agent sessions with YAML artifacts and programmatic validation.

cloudnative-co/claude-code-starter-kit ★ 116
cloudnative-cc-starter

Japanese-language wizard-driven Claude Code setup kit with 3 profiles, Anthropic plugin marketplace integration, and cross-platform (macOS/Linux/Windows) instal…

ClawSpec ★ 43
clawspec

Embed OpenSpec workflow into OpenClaw chat with visible planning, durable background implementation that survives gateway restarts, and channel-scoped project s…

spec-first (sunrain520) ★ 30
spec-first-sunrain

npm CLI + 40 skills + 51 agent reviewers that turns AI coding into a repeatable loop where scripts prepare deterministic facts and LLMs make semantic decisions.

matsengrp/plugins ★ 22
matsengrp-plugins

Gives computational biology teams 12 specialized agents for scientific writing, LaTeX editing, bioinformatics pipelines, and code quality review, with macOS not…

research-kit (nguyenvanduocit) ★ 19
research-kit-nguyenvanduocit

Adapts the spec-kit SDD workflow for systematic 10-phase AI-guided research with source provenance tracking and BibTeX citations.

Harness-Engineering-skills ★ 17
harness-engineering-skills-phlegon

PRD-to-code repo-backed delivery orchestration with three ceremony levels, 19 named agents, filesystem-enforced phase gates, and cross-session state persistence…

Polka Codes ★ 16
polka-codes

TypeScript CLI that provides composable AI coding subcommands with multi-provider routing, checkpoint/resume, and a TypeScript API for meta-workflow scripting.

zbruhnke/claude-code-starter ★ 15
zbruhnke-cc-starter

Prevents vibe-coding via a Wiggum Loop autonomous implementation skill with OS-level git pre-commit enforcement of test/lint/changelog gates.

my-claude-code-harness (code-yeongyu) ★ 13
code-yeongyu-my-cc-harness

Personal Claude Code workflow: plan-to-execute pipeline with Haiku workers, profane attention-weight prompting for atomic task enforcement, and PostToolUse Pyth…

pi-ralph ★ 13
pi-ralph-orch

Add YAML-configurable hat-based multi-phase orchestration loops to the pi coding agent, with event-driven hat transitions and guard rails.

sgaunet/claude-plugins ★ 13
sgaunet-plugins

Four-plugin domain-specialist marketplace (DevOps, software engineering, Go, Bash) with named expert agents and per-agent tool restrictions.

huangdijia/oh-my-claude-code-plugins ★ 10
huangdijia-cc-plugins

Multi-plugin Claude Code marketplace implementing spec-driven development (EARS requirements + Mermaid design + task checklist) with surgical one-at-a-time task…

Prodigy ★ 9
prodigy-iepathos

Turn ad-hoc Claude sessions into reproducible, parallel, checkpointable development pipelines via YAML workflow files.

oh-my-claude (stefandevo) ★ 7
stefandevo-oh-my-claude

Ports oh-my-opencode's Sisyphus multi-agent orchestration to Claude Code natively after Anthropic blocked third-party OAuth access.

anilcancakir/claude-code-plugins ★ 6
anilcancakir-cc-plugins

Seven productivity plugins for Claude Code with strategic-compact as a hook-driven context lifecycle manager that suggests compaction at phase transitions rathe…

oh-my-customcodex (baekenough) ★ 3
baekenough-oh-my-customcodex

Codex-native port of oh-my-customcode: 49 agents, 123 skills, compiled from source using the skills-as-source-agents-as-artifacts metaphor, with dynamic agent c…

claude-code-playbook (toy-crane) ★ 3
claude-code-playbook-toy-crane

Korean-language Claude Code lecture site with QA reviewer agents and student plugin.

maverick ★ 3
maverick-get2knowio

Orchestrates PRD-to-merged-code via a bead dependency graph where agents and humans create work for each other, with enriched review context (spec + contrarian …

OpenSpec-Video ★ 2
openspec-video

Spec-driven AI media production: compile narrative Markdown specs into production-ready images/videos via multi-provider pipeline with dependency graph manageme…

AI Dev Workflow (tkhongsap) ★ 1
ai-dev-workflow-tkhongsap

PRD-driven development workflow + multi-specialist code review system with GitLab MR integration, designed for enterprise teams mentoring junior developers.

opsx-feature-dev ★ 1
opsx-feature-dev

Adds a 7-phase artifact-driven feature development workflow on top of the OpenSpec CLI and Anthropic's official feature-dev plugin.

Vibe Compiler (vibec) ★ 0
vibe-compiler
oh-my-claude-code (zephyrpersonal) ★ 0
zephyrpersonal-oh-my-claude

Cost-aware multi-agent orchestration for Claude Code with magic-keyword Ultrawork mode and YAML-metadata-driven agent routing.

AdaL
adal

Multi-agent engineering system with specialized Worker Agents (coding, research, browser use, review) and an Engineer Agent coordinator for teams

Ptah (Coding Orchestra)
ptah-orchestra
Tars (Gemini CLI ecosystem)
tars-gemini

Unknown — described as a local-first autonomous supervisor sidekick for the Gemini CLI ecosystem.