Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Loop Now: a local multi-agent workspace for running your own team of agents, extensible with plugins | 本地运行的多 Agent 协作平台
GoApache-2.0★ 5No key
Multi-agent GitHub App that resolves merge conflicts with LangGraph + MCP and opens draft PRs only after Docker-sandboxed regression verification.
PythonMIT★ 1Few starsNo key
Mail between coding-agent sessions, on one machine or across machines: an MCP server and CLI on Bun and SQLite.
Node.jsMIT★ 2Few starsNo key
🦅🪽 Sovereign Self-Evolving AI Agent Framework: Hermes closed-loop skill evolution x OpenClaw <1.5K token frugality x Gemini Agent Booster (O(1) Thinking Budget & 90% KV-Cache) x Zero-Trust VM Sandbo
SkillMIT★ 1Few starsNo key
Machine-wide shared memory for AI agents (MCP) — WorkBuddy/Codex/Claude Code/Kilo/OpenCode/DeepSeek Harness
SkillMIT★ 1Few starsNo key
Local-first, zero-key web search MCP server: ddgs multi-engine + semantic search, reader-mode fetch, PDF, sqlite cache, GitHub search
PythonMITFew starsNo key
Shared memory for AI coding agents over MCP: content-hash file summaries, symbol map, notes, handoffs and agent-to-agent messaging. Zero dependencies, one SQLite file.
PythonMITFew starsNo key
Local agent-to-agent messaging over MCP for Codex CLI, Claude Code, and optional LiteLLM API models. SQLite mailboxes, resumable sessions, and two-way conversations.
PythonMITFew starsNo key
Coopagents — multiplayer mode for Claude Code and Codex. Your agents and your teammates' agents share one task board, ask each other questions, hand off work and wake each other up. Peer-to-peer, no s
SkillMIT★ 2Few starsNo key
Token-budgeted, drift-aware MCP memory engine for AI coding agents. Backed by SQLite WAL + FTS5 BM25, Git-anchored drift webhooks, and 1-click onboarding.
SkillAGPL-3.0Few starsNo key
Who stands behind it