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.
Run coding agents anywhere and keep one record of the work, with tools and memory in sync across your harnesses. Local files, no daemon.
PythonMIT★ 81No key
A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and delivers efficient AI coding assistance through hierarchical memory
SkillMIT★ 117No key
ChatGPT <-> Codex bridge: local coding agents ask ChatGPT for advice, and ChatGPT can inspect or steer your running Codex sessions. No API key.
PythonMIT★ 13No key
Agent-first SSH orchestration MCP server: persistent bash sessions, hash-protected remote file editing, SFTP, SSH tunnels, and multi-host orchestration. Built on AsyncSSH + FastMCP with an in-process
PythonApache-2.0★ 7No key
Lightweight browser automation CLI + MCP server driving your everyday Chrome via the extension chrome.debugger API — keeps your login state, no --remote-debugging-port
SkillMIT★ 5No key
Local-first MCP memory governance for coding agents — Codex, Claude Code, Cursor, Grok, and Trae. Shared rules, deduplication, token insights, audit, and rollback.
SkillMIT★ 4Few starsNo key
Secure SSH gateway for AI assistants — MCP server with connection pooling, session isolation, command safety, and web audit panel
PythonMIT★ 4Few starsNo key
CONtext comPACT coordinates agent-initiated context compaction at verified scope closure—after the final answer and a durable checkpoint. It compacts the live context without clearing the visible conv
PythonMIT★ 3Few starsNo key
Persistent memory graph for AI coding agents — semantic search, knowledge graph, and time-based decay over MCP
PythonMIT★ 5No key
Memory management for AI agents through project phases
PythonMIT★ 2Few starsNo key
Model Context Protocol server for Herdr: full remote control of workspaces, tabs, panes, agents and worktrees. Dependency-free Python.
PythonMIT★ 2Few starsNo key
A Model Context Protocol (MCP) server that enables AI models to manage SSH connections and execute commands on remote machines without repeatedly entering credentials.
PythonMIT★ 3Few starsNo key
Agentic OS that runs on any Linux — curated knowledge API for AI agents: MCP tools, skill packs, semantic search. Works with Claude Code, Cursor, Cline, Windsurf.
PythonMIT★ 7No key
Give AI agents orchestration capabilities with an iTerm2 MCP server for macOS. Coordinate Claude Code, Codex CLI, and other coding agents across terminal sessions: delegate tasks, monitor progress, se
PythonMIT★ 1Few starsNo key
Desktop app for running and managing Coding Tools MCP.
PythonApache-2.0★ 1Few starsNo key
Queryable memory for coding agents: capture every session, recall exact evidence, and sync it end-to-end encrypted across devices and teams.
SkillMIT★ 1Few starsNo key
Self-hosted LLM gateway and AI context firewall for PII/PHI containment, prompt-injection defense, and governed agent tools.
PythonMIT★ 1Few starsNo key
Local-first persistent memory for AI coding agents across Claude Code, Codex, OpenCode, Cursor, and more.
PythonMIT★ 1Few starsNo key
Self-organizing agent memory for OpenClaw — SQLite + FTS5 + vector embeddings + LLM extraction
SkillMIT★ 2Few starsNo key
Centralized Remote Model Context Protocol (MCP) server providing real-time microservices architecture intelligence, APIs, and change blast-radius analysis for AI coding assistants.
PythonMIT★ 1Few starsNo key
A unified context layer that connects your local data — repositories, documents, remote machines, and notes — to LLM interfaces through the Model Context Protocol (MCP).
PythonMIT★ 3Few starsNo key
MCP bridge for connecting coding agents to remote A2A agents, with an optional local activity dashboard
PythonMITFew starsNo key
Who stands behind it