The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

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.

Real-time agent to agent communication

A modernised git interface for improved agent and human collaboration, review and control

A Multi-Agent platform that enables AI agents to collaborate effectively, helping you build powerful agent teams for solving complex tasks.

Learn to build and customize multi-agent systems using the AutoGen. The course teaches you to implement complex AI applications through agent collaboration and advanced design patterns.

AI Agent Team SKILL - 基于 newtype-profile 架构的 AI Agent 协作系统

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

Collaborative application security testing between humans and agents via CLI and MCP

API and WebSocket chat rooms where Claude Code, Codex, Pi and Opencode agents communicate via persistent messages. Humans can watch and participate through the web UI.

A production-grade Python client for the Swarms API, providing a simple and intuitive interface for creating and managing AI swarms.

Shared workspace for solo developers working with agents. Manage tasks and knowledge in the web UI, let agents use the same data through skills, and keep simple CRUD out of chat.

NEXUS（Networked Emergent X-agent Universe Simulator） 是一个面向复杂信息环境分析的多智能体 AI 框架，旨在通过多智能体协同与知识驱动推理，对现实世界不断演化的信息流进行深度理解与模拟。系统整合了领域适配微调模型、客制化深度搜索 Agents、用户注意力驱动 Agents以及数字孪生仿真环境 Canyon，构建了一个能够持续获取、组织并分析信息的智能系统。在该架构下，NEXUS 可以从多源信息中提取关键实体与关系，结合领域知识先验与用户关注锚点，对复杂事件、舆论动态与叙事演化进行多视角分析与推演。通过优化推理流程与 Agent 协作机制，系统在降低 tokens 消耗的同时保持较强的分析深度。

Join.cloud lets AI agents work together in real-time rooms. Agents join a room, exchange messages, commit files to shared storage, and optionally review each other's work — all through standard protocols (MCP and A2A).

🐝 Dynamic multi-agent collaboration system with emergent roles, cognitive alignment, and deliverable-driven output. Make AI collaborate like an elite consulting team.

Public logging system for AI Village interactions with external autonomous agents

Local-first AI memory system and multi-agent control plane for persistent context, project routing, and long-term knowledge.

Distributed Multi-Agent AI Orchestration with Ollama - Advanced collaborative workflow with AST quality voting, TrustCall validation, and adaptive strategy selection

Skill-as-API: P2P agent collaboration over XMTP. Call remote skills without exposing code. E2E encrypted, revocable trust, async delegation. Zero deps.

Agent discovery hub for AI Village - Machine-readable information for external agents to find and interact with us