Explore
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
faultkitfaultkit
Local
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Prove your AI agent fails safely. Fault injection for LLM, RAG, and tool-call failures: declare what must never happen, find the silent failures, and keep the proof on every pull request.
SkillApache-2.0★ 3Few starsNo key
Simulate, test, and validate AI agent integrations — without calling real LLMs or burning tokens.
GoApache-2.0★ 1Few starsNo key
Honeypot canaries for AI agents. Detect compromised agents via fake credentials that phone home when used.
GoApache-2.0★ 5No key
Federated, evidence-first retrieval for personal AI agents
GoApache-2.0★ 1Few starsNo key
Terminal UI engine for Go that tests can click and AI agents can drive (MCP). Zero-allocation rendering, immediate mode + Elm architecture, 3D, images, charts, accessibility, WebAssembly.
GoApache-2.0★ 167No key
Traceability gate for coding agents: blocks "done" until every requirement has a passing test. Hooks into Claude Code, Codex, Copilot, Cursor, Gemini CLI and more; works with pytest, Jest, Vitest, JUn
SkillApache-2.0★ 1Few starsNo key
OpenChoreo is an internal developer platform for Kubernetes
GoApache-2.0★ 1.7kNo key
Deny-wins policy hook for Claude Code and Codex. Checks every shell, file, and fetch call against rules you keep in Git, holds under --dangerously-skip-permissions, refuses commands it cannot parse, a
GoApache-2.0★ 19No key
MCP server that gives AI coding agents (Claude Code, Cursor, etc.) full control over Unreal Engine 5.7 projects — headless builds & tests, Blueprint editing, actor manipulation, procedural mesh genera
GoApache-2.0★ 78No key
Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flags when the agent's summary says all tests pass but something
SkillApache-2.0★ 17No key
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
GoApache-2.0★ 429No key
Model your API as a graph once. Long-chain integration tests, layer × environment matrices, CI-ready runs, and an MCP server — all from the same YAML.
GoApache-2.0★ 5No key
Taichi is a language-agnostic, plugin-driven test orchestration framework — run API, gRPC, UI, static, and regression tests with one CLI, extend via third-party skill plugins in any language, integrat
GoApache-2.0★ 1Few starsNo key
Model Context Protocol (MCP) server for Go using gopls – LSP-powered analysis, tests, coverage, and tooling.
GoApache-2.0★ 104No key
OfficialGoApache-2.0★ 9No key
A local tool-output compressor for **Claude Code and Codex**. TokenSlim reduces repetition in builds, tests, and logs, preserves diagnostics, and caches the original output. It does not modify source
SkillApache-2.0★ 2Few starsNo key
Production Kubernetes operator for deploying and validating MCP servers
GoApache-2.0★ 29No key
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
GoApache-2.0★ 36No key
Shared Android Instrumented Runner: Enables junit5 tests to be run by multiple orgs / repos etc. on a shared set of android devices
GoApache-2.0★ 1Few starsNo key
Who stands behind it
