MCP servers and skills: search, filter by where they run, and compare.
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
Node.jsApache-2.0★ 6.2kNo key
Anti-detection browser server for AI agents — REST API wrapping Camoufox engine with OpenClaw plugin support
Node.jsMIT★ 422No key
Measurable image + document toolkit. Bit-exact SVG from flat art (SSIM 1.0000, verified by rendering it back); beats potrace, imagetracerjs and vtracer on photographs. 11 raster formats, every pair co
Node.jsMIT★ 17No key
Local MCP server for deterministic project code, document, and handoff context.
Node.jsMIT★ 1Few starsNo key
Tools for AI agents to test, fix and optimise your codebase
Node.jsApache-2.0★ 48No key
TypeScript AI agent framework — 40+ LLM providers, 100+ tools, multi-agent orchestration, RAG, guardrails, circuit breakers, HITL, budget enforcement. Open-source CrewAI / LangChain alternative. — For
Node.jsMIT★ 10No key
Open source LLM observability and monitoring. Drop-in proxy for OpenAI, Anthropic, and Gemini with request logging, cost tracking, and agent tracing. Self-host with one Docker command. MIT.
Node.jsMIT★ 13Needs a key
Open-source statement-level Playwright tracer, purpose-built for AI agents. Analyzes test runs with increased accuracy.
SkillAGPL-3.0★ 46No key
A token-frugal MCP server that gives coding agents structural understanding of a codebase: repo maps, symbol outlines, ranked search, import tracing, and parsed diagnostics — every result under a toke
Node.jsMIT★ 4Few starsNo key
Local MCP (Model Context Protocol) server for integrating LLMs with Mackerel.
Node.jsApache-2.0★ 7No key
元谨是一套通用的「防 AI 敷衍」规则引擎技能，适用于开发、写作、数据分析、架构设计等所有场景。它通过「先分析 · 再执行 · 后自检」的强制流程，遏制表面化输出：复杂任务必须先给出含根因 / 推理 / 影响范围 / 不确定性的分析报告；推测性结论须附带置信度声明；任务结束强制自检并主动暴露疑虑；用户一句「停」即可触发重新分析。规则可临时关闭，但「信息不足须明说」与「打断必重来」为不可关闭的底线。
SkillMIT★ 6No key
POSIX-native MCP server for intercepting DNS escapes and enforcing deterministic domain resolution for autonomous agents.
Node.jsMIT★ 8No key
Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.
Node.jsMIT★ 9No key
Wayd is an intelligent delivery management platform designed to give leaders and teams end-to-end visibility into software delivery.
SkillMIT★ 7No key
A companion MCP server and CLI to StyleSafe that makes CSS legible to AI agents — resolving cascade, tracing properties, and explaining what applies and why before an agent touches a single line.
Node.jsMITFew starsNo key
SkillMIT★ 2Few starsNo key
A community-driven library of reusable AI agent skills for Claude Code, Cursor, Codex, Cline, and more.
SkillMIT★ 9No key
Node.jsMITFew starsNo key
Preview, clean up, vectorize & export your logo — 100% in your browser. No uploads, no sign-up.
Node.jsMIT★ 1Few starsNo key
Your AI forgets everything between sessions. This fixes that — 98%+ retrieval accuracy, 100% on LongMemEval, 99% token savings. 44 MCP tools. Fully local, zero cost.
Node.jsMIT★ 19No key
OpenTelemetry observability for LLM systems — auto-instrumentation (OpenAI, Anthropic, Gemini, Vercel AI SDK), cost tracking, budget guards, agent tracing, OTel GenAI semconv, 8 Grafana dashboards. On
MCPLink only★ 2Few stars
Debug logging and protocol tracing for stdio-based MCP servers
Node.jsMITFew starsNo key
Who stands behind it
