MCP servers and skills: search, filter by where they run, and compare.
A modular repository for experimenting with LangChain, LLM-powered Agents, and Autonomous AI Workflows. It contains practical implementations, mini-projects, and research-based prototypes.
SkillMIT★ 1Few starsNo key
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
SkillApache-2.0★ 23kNo key
Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Importance scoring, contradiction resolution, confidence-aware
PythonApache-2.0★ 49No key
The definitive OpenAI, Claude, MCP, Harness, Evals, and Production Agent Systems learning roadmap.
SkillMIT★ 568No key
Agent skills for Arize — datasets, experiments, and traces via the ax CLI
SkillMIT★ 66No key
Open-source AI phone API for voice agents. Give Claude, Cursor, OpenClaw, or any LLM a real phone number — outbound/inbound calls, SMS, transcripts, MCP, DTMF/IVR. FastAPI + SignalWire + Deepgram. Sel
SkillMIT★ 56No key
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, Gi
PythonApache-2.0★ 17No key
AI security testing — find security vulnerabilities in LLM apps, chatbots, AI agents, MCP servers, and RAG systems. Mapped to OWASP (LLM, Agentic, MCP) and NIST AI RMF.
SkillMIT★ 2Few starsNo key
Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
PythonMIT★ 23No key
Local-first prompt regression testing and evals for LLM apps.
PythonMIT★ 4Few starsNo key
Real-time AI safety guardrails for LLM apps. 10 scanners: prompt injection, PII, harmful content, code vulnerabilities, obfuscation detection. Sub-ms latency. Python + TypeScript SDKs. MCP proxy. Clau
PythonApache-2.0★ 25No key
Vendor-neutral token-reduction layer for LLM apps and coding agents: AST code retrieval, prefix caching, compression with a deterministic fact-guard, and cascade. Measured, quality-neutral. Works as a
PythonApache-2.0★ 2Few starsNo key
AI model health monitor for LLM apps – runtime checks for drift, hallucination risk, latency, and JSON/format quality on any OpenAI, Anthropic, or local client.
MCPLink only★ 18
A comprehensive MCP server for the [Tesla Fleet API](https://developer.tesla.com/docs/fleet-api). Control and monitor any Tesla vehicle (Model S/3/X/Y, Cybertruck, Semi) via Claude, Claude Code, Curso
PythonMIT★ 1Few starsNo key
Your AI wrote the code. Who checked it? 9 security agents + 185 rules audit vibe-coded apps (Supabase, Next.js, Firebase, LLM apps), then plan the fix and verify it. Offline, no API key.
SkillApache-2.0★ 2Few starsNo key
Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gate
PythonApache-2.0★ 13No key
一站式修复大模型 SSE 流式输出中文乱码、Markdown 渲染异常 / Fix Chinese garbled text, Markdown rendering & SSE streaming issues in LLM apps
SkillApache-2.0★ 2Few starsNo key
Production-ready Claude Code configuration. 12 original agents, 200+ slash-command skills, 45+ MCP servers, 14 plugins, design + 3D + WebGPU + GSAP + RAG tooling. One-command Node.js installer for pre
Node.jsMIT★ 7No key
The plug-and-play evals layer for LLM-based projects: library, learning center, check center, API, MCP server.
SkillMIT★ 1Few starsNo key
Curated AI agent evaluation skills from Microsoft's Eval Guide — plan, generate, run, and interpret eval suites for Copilot Studio agents
SkillMIT★ 1Few starsNo key
Know what your AI costs: pricing and spend for Claude, GPT and Gemini.
Node.jsMITFew starsNo key
An MCP (Model Context Protocol) server that bridges LLM applications (like Claude Code) with language servers (like rust-analyzer) to enable semantic code navigation.
SkillMIT★ 2Few starsNo key
MCP security scanner (CLI + MCP server): detects tool poisoning, prompt injection, and rug-pulls in MCP manifests. Also an OWASP LLM Top 10 prompt-injection/jailbreak CLI for LLM apps.
Node.jsMIT★ 1Few starsNo key
Glif — independent third-party profile of a public API surface, by API Evangelist. Glif is a creative AI platform from Spellcasters, Inc. — originally launched in 2023 as a no-code visual workflow bui
MCPLink only★ 2Few stars
Who stands behind it
