Browse the library

ruflo

ruvnet

Ruflo is an agent meta-harness that provides a "nervous system" for Claude Code and Codex, enabling self-organizing multi-agent swarms, adaptive memory, and federated communication.

This agent tool, OmO, provides multi-model ultracode capabilities and an improved memory system, turning prompts into finished work like research, presentations, and code.

Provides multi-agent orchestration for Claude Code, enabling teams to manage and run multiple AI agents with a zero learning curve.

An open-source desktop application for building and managing a multi-agent AI workforce with MCP and skill integration, featuring browser and terminal toolkits.

hive

aden-hive

This agent harness provides a model-agnostic runtime for managing colonies of AI agents, enabling reliable and scalable execution of complex business processes.

This meta-skill for Claude Code designs domain-specific agent teams, defines specialized agents, and generates their skills, supporting various execution modes and quality patterns.

openrig

mvschwarz

Enables building and orchestrating networks of AI coding agents like Claude Code and Codex into persistent teams with shared context.

Connects the ChatGPT web app to Codex via a read-only MCP, allowing ChatGPT to act as the planning and review brain for Codex coding sessions.

Helps design AI agent workflows visually on a canvas and exports them as Markdown for agents like Claude Code and Cursor to understand.

Orchestrates multiple AI models (Claude, Codex, Copilot, Gemini, etc.) to perform research, design, or coding tasks and surface disagreements before shipping.

Vibe-Skills offers intelligent skill routing and workflow orchestration for AI agents, significantly improving task completion and reducing token consumption on benchmarks.

agency-orchestrator

jnMetaCode

This orchestrator enables AI agents to form a "one-person company" team based on a single prompt, delivering complete solutions with auto-verified acceptance.

This skill allows an AI orchestrator to delegate coding tasks to specific AI implementer CLIs based on work type, with human review of the diff.

Orchestrates and manages teams of AI agents from various platforms like Claude Code and Cursor for collaborative project work.

Enables AI agents to execute complex, multi-step workflows deterministically across various AI coding harnesses, enforcing obedience and ensuring quality gates.

Keeps specialist agents in a hub and spins up a temporary orchestrator per task, running inside Claude Code, Codex, Cursor and Gemini.

Octogent is an orchestration dashboard for Claude Code, managing context, automating tasks, and enabling multi-agent coordination.

A CLI that uses YAML to define repeatable multi-step workflows for AI coding agents with isolated environments.

This orchestrator allows AI coding agents like Claude Code and Cursor CLI to work together in parallel or sequence within isolated tmux sessions.

A pi extension that brings Claude Code-style autonomous sub-agents and workflow orchestration, supporting parallel execution and mid-run steering.

This experimental system enables temporary collaboration rooms where humans and AI agents can exchange context and tasks, then disappear without requiring permanent workspaces.

Orchestrate multiple coding agents and humans in a structured pipeline where agents propose and humans verify.

alook

alookai

This platform gives your local AI coding agents persistent identities and shared rooms, enabling collaboration and communication with people on your team.

AgentRQ is a self-hosted, human-in-loop task manager for AI agents that uses MCP to enable real-time collaboration and task delegation via visual boards and workflows.