MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Shared engine for the benchmark-* family: runner, graders, model adapters, CLI, MCP server and HTTP API from one definition.
Hosted by authorMITFew starsNo key
Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reprodu
PythonApache-2.0★ 305No key
Open, reproducible framework for measuring, comparing, routing and verifying bounded work across heterogeneous LLMs via MCP.
DockerApache-2.0Few starsNo key
Local-first agent harness (Windows + Ollama) for 2–9B models. Same 2B model: 0.017 → 0.821 across four agent harnesses — 48×. 288-cell benchmark, every cell public. One-click zero-outbound mode. 本地优先，
SkillApache-2.0★ 21No key
Portable WPE WebKit runtime for AI agents with native input, screenshots, ordered JSONL, and reproducible benchmarks.
DockerApache-2.0★ 2Few starsNo key
Open source AI agent harness & agentic AI runtime in TypeScript. 6-phase state machine, 24 tools, human-in-the-loop permissions, MCP server, and composable agent APIs. Zero dependencies.
Node.jsMIT★ 2Few starsNo key
Node.jsCC-BY-4.0Few starsNo key
The Agent Skill for cross-browser extension development. Teaches AI coding agents to build, debug, and publish for Chrome, Edge, Firefox, Safari, and every Chromium- or Gecko-based browser.
SkillApache-2.0Few starsNo key
Give your agent a body: Embodify lets it control robots directly and become your embodied agent. Your best embodied agent is your favorite agent — with its memory, its tools and everything it knows ab
PythonApache-2.0★ 5No key
Node.jsMITFew starsNo key
A portable agent skill and evaluation framework that produces purposeful, distinctive design with intent.
SkillMITFew starsNo key
Evidence-first entity and knowledge graph MCP server for AI agents to verify claims, trace cryptographic provenance, and retrieve 90% less context.
Node.jsMIT★ 1Few starsNo key
Probe RL environment verifiers for false passes and false fails
PythonApache-2.0★ 1Few starsNo key
LayerMap MCP: a layered map of your codebase for coding agents: callers, callees and the impact of a change, for TypeScript, JavaScript, Go, Python and Java. MCP server, CLI, and plugins for Claude Co
Node.jsApache-2.0★ 6No key
Node.jsMITFew starsNo key
Public API, Python client and MCP server for Clousd cloud Android phones.
PythonMIT★ 1Few starsNeeds a key
Real-time offline dubbing for macOS — capture any app, transcribe, translate and speak locally.
SkillMIT★ 7No key
Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.
Node.jsMIT★ 5No key
Agent skill for UI/UX design and review using behavioral design principles — canonical standalone source for bizar-uiux.
SkillMIT★ 3Few starsNo key
Offline $0 decision layer for coding agents: Choice/Score/Noul primitives, BELKI confidence gatekeeper, ultra-planning, red-teaming, research and RLVR self-improvement -- as an MCP server + CLI + Clau
Node.jsMIT★ 4Few starsNo key
Let your coding agent drive the iOS Simulator, and tell it the truth about what happened.
SkillApache-2.0★ 3Few starsNo key
Let AI agents drive iPhone and Android devices from the shell: read the screen, tap, type, swipe, screenshot, logs and crashes. No server, zero dependencies.
Node.jsAGPL-3.0Few starsNo key
Implicit is the experience layer for AI agents.
PythonApache-2.0Few starsNo key
Who stands behind it
