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.
Druks runs agent apps on your own infrastructure: durable runs that survive restarts, human approvals, and full history. Apps install as Python packages.
PythonMIT★ 17No key
Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop
PythonApache-2.0★ 8No key
A full agent framework on the Vercel AI SDK, durable from the core: exactly-once tool calls, deterministic replay, time-travel.
Node.jsApache-2.0★ 2Few starsNo key
Django DRF's developer experience. Fully async. Built on FastAPI. With native MCP tooling and column-level control over what your LLM can see.
PythonMIT★ 18No key
Build and operate production-safe agents that run in your own environment.
PythonApache-2.0★ 17No key
Durable MCP Tasks on infrastructure you already own — local, SSH, and Slurm.
PythonMIT★ 1Few starsNo key
Next-Generation Multi-Agent Collaboration Platform and Workflow Engine. Build and orchestrate production-ready AI agent teams with sandboxed execution, hybrid RAG, and enterprise-grade security.
SkillGPL-3.0★ 19No key
A runtime for reliable multi-agent systems with durable workflows, resumable execution, and human-in-the-loop control
GoApache-2.0★ 4Few starsNo key
Vendor-neutral graph orchestration for reliable agentic systems: one portable Graph IR, native TypeScript/Python runtimes, deterministic barriers/routers, and cross-language conformance.
SkillMIT★ 4Few starsNo key
infinite token glitch - mcp server for chatgpt to use codex tools on a real machine
SkillApache-2.0★ 4Few starsNo key
Durable temporal event intelligence for agent runtimes — host-owned MCP event discovery, composite triggers, derived events, and targeted wakeups.
Node.jsApache-2.0★ 1Few starsNo key
TypeScript agent framework with zero runtime dependencies — agents, memory, workflows, durable agents, signals, schedules. Now chasing mastra's proven feature surface inside that lightweight axis — se
Node.jsApache-2.0★ 1Few starsNo key
The open-source checkpoint layer for AI agents — checkpoints, replay, durable queues, cron, cancellation, gates, and live state, in your own Postgres.
MCPLink only★ 1Few stars
Full-stack framework for building AI apps and agents with TypeScript and React. Works with Node.js, Deno, and Bun.
SkillApache-2.0★ 19No key
Use your ChatGPT or Claude Web quota for remote coding without a second server-side API token meter
SkillMIT★ 18No key
Protocol for agent-to-agent communication with stateful orchestration, MCP-compatible and a public marketplace to discover and register agents.
PythonApache-2.0★ 16No key
Durable task delegation for Pi Coding Agent over MCP, with background execution, steering, and crash recovery.
Node.jsMIT★ 12No key
Local-first runtime for coding agents. Agents file tasks, Orbit lands them from sandboxed worktrees, and every step is audited. Works with Claude Code, Codex, Cursor and more.
Node.jsMIT★ 14No key
Open-source local MCP execution runtime for agents: policy-gated tool calls, scoped approvals, verified outcomes, durable receipts, and recovery after interruptions.
Node.jsApache-2.0★ 11No key
Operating layer for durable AI work — mandates, evidence and human decisions across replaceable AI execution.
SkillApache-2.0★ 4Few starsNo key
Model Context Protocol servers for the official Robinhood Crypto Trading API — the credentialed brokerage API at trading.robinhood.com, documented at docs.robinhood.com/crypto/trading.
Node.jsApache-2.0★ 9No key
Reference architecture and working case study for Codex × Antigravity agent-runtime collaboration.
SkillMIT★ 11No key
Who stands behind it