Multi-agent orchestrator
Spawns N agents in parallel or hierarchical patterns. Worktrees, swarms, queens+workers.
44 primary frameworks · 64 lower-confidence entries
Self-improving personal AI agent with closed learning loop, 7 terminal backends, and messaging gateway — not tied to any AI coding tool.
Terminal-first AI coding agent with multi-model routing, native desktop app, and a typed .opencode/ configuration system for agents, commands, skills, and…
Open-source AI software development platform (open-source Devin alternative) with Docker sandbox isolation, 77.6% SWE-bench score, and 25+ trigger-activated…
Long-horizon superagent that researches, codes, and creates by orchestrating parallel sub-agents with isolated contexts in Docker sandboxes, driven by…
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.
Eliminates single-agent context limits and sequential bottlenecks by orchestrating fault-tolerant swarms of specialized AI agents with shared persistent memory.
ARCHIVED — the original LLM-driven code generation experiment that generates entire applications from a prose specification file.
Terminal-native AI pair programming with git-first edit semantics and automatic commit messages.
AI code review as source-controlled, enforceable CI checks — green/red GitHub status checks powered by markdown-defined agent instructions.
Add structured planning, durable state, and multi-agent team coordination to OpenAI Codex CLI without replacing it.
154+ domain-specialized Claude Code subagents across 10 categories, installable as plugins with no commands, skills, or hooks — pure agent catalog.
Use OpenAI Codex as a reviewer and task executor from inside an active Claude Code session without leaving the CC workflow.
Research-grade GitHub issue fixing agent with YAML-configurable prompts, one-command-at-a-time REPL loop, and batch evaluation support for SWE-bench…
Coordinate 20-30 concurrent AI coding agents on shared repos with persistent work state, crash recovery, and autonomous health monitoring.
Two-workflow Claude Code spec harness: structured feature development plus dedicated bug-fix pipeline, with a real-time dashboard and Tauri desktop app for…
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…
216+ slash commands across 26 domain namespaces + 12 skills + 54 agents covering full-stack development, DevOps, security, media processing, browser AI, and…
Full-stack agent harness with Reversed Conversation philosophy — AI proposes, humans verify — enforced via a permission-gated MCP server and production web UI
Official Cursor plugin marketplace providing CI workflows, engineering principles, parallel cloud-agent orchestration, transcript-based memory, and iterative…
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…
Bridge Claude Code's 60+ production-tested skills to Roo Code via an orchestrator mode and CLI skill-discovery tool.
Iteratively refines product specifications through multi-LLM adversarial debate until all models reach consensus, surfacing gaps and edge cases that any single…
Turn a vague feature idea into structured specs and then execute them task-by-task with fresh subagent context, without losing state across sessions.
12-role musical-metaphor hierarchy (Composer→Score→Conductor→Performer) for Roo Code, with three automation levels, Mermaid visualization, and append-only…
Cursor-native SDD toolkit with async background subagent trees, parallel DAG execution with file-conflict detection, checkpoint-resume, and downstream spec…
Decompose complex tasks via Opus into a dependency DAG, execute waves of Haiku workers in parallel, then Opus quality-gates the combined output — mirroring…
Generates EARS-formatted specs via parallel codebase exploration agents before any implementation begins, ensuring specs reflect actual code patterns.
Hub-and-spoke hierarchical orchestration for OpenCode with Chase-Lev work-stealing, MVCC state sync, and evidence-based anti-hallucination mandates.
Decentralized swarm orchestration for parallel Claude Code agents using GitHub Issues as the atomic task queue and git worktrees for zero-conflict isolation.
Empirically proves that Claude Code pre-configuration improves output quality by 60% across 15 software engineering tasks.
A focused Codex-only workflow runtime with tmux team execution, MCP servers, and durable .omx/ state — the v2 vision without Claude bridge.
Enforce Director/Coder split via adaptive hook-based delegation nudges, native plan mode as the handoff boundary, and 8 specialized agents for domain execution.
Context-Driven Development plugin that enforces a spec-plan-implement lifecycle with Python-CLI context management, pattern library, and ADR logging for Claude…
Coordinates 11 specialized AI agents with adversarial code review, JWT agent identity, and 6-provider multi-model routing against shared SQLite memory.
375 aggregated skills + 155 droids from 15+ repos covering AI/ML, scientific research, and development — targeting both Claude Code and Factory's Droid system.
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.
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…
Stop asking AI agents to remember process — install risk-routing, evidence-gated completion, and explicit subagent contracts as automatic hooks.
Simplified Context-Driven Development plugin with 3-agent specialization (planner/implementer/reviewer) and lifecycle hooks for passive context management.
A personal Codex plugin extension adding tier-based model routing, LSP/AST tooling, and notification integrations to the canonical oh-my-codex workflow.
Codex-native 13-stage pipeline with context-isolated subagents that prevents assumption drift in large multi-file changes.
Eliminates the duplicate artifacts and manual skill selection overhead of using OpenSpec and Superpowers together by providing a schema that enforces their…
Exact copy of lackeyjb/claude-conductor with spam README; no independent value.
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.
Minimal, extensible TypeScript terminal coding agent with multi-provider LLM API, TUI library, and TypeScript Extension API — adapt to workflows without forking…
Build, deploy, and manage production agent platforms with full ownership of data, memory, and compute.
npm-installable marketplace of 600+ Claude Code agents, commands, hooks, MCPs, and settings for composable workflow assembly.
Run an AI coding tool in a fresh-context loop, one user story at a time, until all stories in prd.json pass.
Bring FastAPI's ergonomics (typed dependency injection, Pydantic validation, IDE auto-completion) to Python agent development.
Cross-platform Electron desktop for autonomous multi-agent coding with kanban UI, parallel git worktrees, self-validating QA loop, and GitHub/Linear integration…
Auto-generate and execute self-healing multi-agent DAGs for complex business workflows from a natural language goal.
Production-grade Claude Code autonomous loop with dual-condition exit gate, rate limiting, circuit breaker, session management, and live monitoring.
TypeScript-native AI agent framework with typed contracts, composable guardrails, and a cloud ops console.
Build durable, composable agents using MCP as the only protocol, implementing every pattern from Anthropic's Building Effective Agents paper.
Run AI agents and full-stack web apps from a single Go binary with TypeScript hooks, container sandboxing, and GraphRAG — zero runtime dependencies.
Zero-config one-command setup for Claude Code + BMAD methodology + API relay provider configuration.
Build persistent, stateful AI agents backed by Cloudflare Durable Objects — scale to millions of instances, each hibernating at zero cost when idle.
Kubernetes-native multi-agent platform where Worker and Manager agents collaborate in a Matrix IM room with enterprise credential isolation via Higress AI gatew…
AI agents generate code matching your team's patterns by loading project context before every execution.
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…
Bridge MCP tool protocol to LangChain/LangGraph BaseTool interface with zero boilerplate.
Define multi-agent AI systems in YAML, package via OCI, and run with Docker — no code required.
Managed cloud infrastructure for deploying AI agents at production scale — eliminating undifferentiated heavy lifting of compute, memory, identity, and security…
Google's official CLI and skill pack for building production ADK agents — enforcing scaffold-first, eval-driven development across Claude Code, Gemini CLI, Code…
Terminal mission control for managing fleets of parallel AI coding agent sessions with fork, MCP, conductor, and worktree support.
Add enterprise-grade instrumentation, profiling, evaluation, and RL fine-tuning to any AI agent framework without migrating your code.
Provides an asynchronous mail-like coordination bus (identities, inboxes, file leases, Git-auditable messages) so multiple coding agents can work the same codeb…
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…
Japanese-developed Claude Code plugin delivering 40+ commands covering requirements (EARS) → design → TDD → implementation → verification for full project lifec…
Takes a spec (PRD/issue/OpenAPI) and autonomously produces a production-ready Git repository through RARV cycles, 11 blocking quality gates, and 41 specialized …
Autonomously optimize code through parallel tree-search experiments with shared state, gate-validated results, and configurable frontier strategies.
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…
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…
Gives a lead AI agent a Go CLI + git worktree infrastructure to dispatch parallel worker agents, track progress, and orchestrate merges without user involvement…
Turns tickets into working code via AI agents that autonomously claim tickets, execute versioned workflow harnesses, and pass lifecycle hook quality gates.
48-plugin personal productivity OS with flagship multi-agent TDD skill implementing information isolation between test-writing and implementation phases.
Teaches Claude Code to delegate tasks to Gemini 3 Pro via CLI for second opinions, Google Search grounding, and codebase architecture analysis.
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…
Spec-driven 4-phase planning workflow for iOS/macOS Swift development in Claude Code, with quality-specialized subagents for accessibility, localization, and mo…
Adds three-reviewer quality gate chain (advisor+critic+risk-assessor) and Python-hook enforcement layer to Claude Code before execution.
Go CLI that orchestrates spec → plan → tasks → implement in fresh isolated agent sessions with YAML artifacts and programmatic validation.
Japanese-language wizard-driven Claude Code setup kit with 3 profiles, Anthropic plugin marketplace integration, and cross-platform (macOS/Linux/Windows) instal…
Embed OpenSpec workflow into OpenClaw chat with visible planning, durable background implementation that survives gateway restarts, and channel-scoped project s…
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.
Gives computational biology teams 12 specialized agents for scientific writing, LaTeX editing, bioinformatics pipelines, and code quality review, with macOS not…
Adapts the spec-kit SDD workflow for systematic 10-phase AI-guided research with source provenance tracking and BibTeX citations.
PRD-to-code repo-backed delivery orchestration with three ceremony levels, 19 named agents, filesystem-enforced phase gates, and cross-session state persistence…
TypeScript CLI that provides composable AI coding subcommands with multi-provider routing, checkpoint/resume, and a TypeScript API for meta-workflow scripting.
Prevents vibe-coding via a Wiggum Loop autonomous implementation skill with OS-level git pre-commit enforcement of test/lint/changelog gates.
Personal Claude Code workflow: plan-to-execute pipeline with Haiku workers, profane attention-weight prompting for atomic task enforcement, and PostToolUse Pyth…
Add YAML-configurable hat-based multi-phase orchestration loops to the pi coding agent, with event-driven hat transitions and guard rails.
Four-plugin domain-specialist marketplace (DevOps, software engineering, Go, Bash) with named expert agents and per-agent tool restrictions.
Multi-plugin Claude Code marketplace implementing spec-driven development (EARS requirements + Mermaid design + task checklist) with surgical one-at-a-time task…
Turn ad-hoc Claude sessions into reproducible, parallel, checkpointable development pipelines via YAML workflow files.
Ports oh-my-opencode's Sisyphus multi-agent orchestration to Claude Code natively after Anthropic blocked third-party OAuth access.
Seven productivity plugins for Claude Code with strategic-compact as a hook-driven context lifecycle manager that suggests compaction at phase transitions rathe…
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…
Korean-language Claude Code lecture site with QA reviewer agents and student plugin.
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 …
Spec-driven AI media production: compile narrative Markdown specs into production-ready images/videos via multi-provider pipeline with dependency graph manageme…
PRD-driven development workflow + multi-specialist code review system with GitLab MR integration, designed for enterprise teams mentoring junior developers.
Adds a 7-phase artifact-driven feature development workflow on top of the OpenSpec CLI and Anthropic's official feature-dev plugin.
Cost-aware multi-agent orchestration for Claude Code with magic-keyword Ultrawork mode and YAML-metadata-driven agent routing.
Multi-agent engineering system with specialized Worker Agents (coding, research, browser use, review) and an Engineer Agent coordinator for teams
Unknown — described as a local-first autonomous supervisor sidekick for the Gemini CLI ecosystem.