MCP servers and skills: search, filter by where they run, and compare.
Prompt-regression and evaluation tracker with a local MCP interface. Compare prompts, keep evidence, leave the release decision to a human.
PythonMITFew starsNo key
Correct Claude once. It stays corrected. A Claude Code skill that turns corrections into tested, tamper-proof hook guardrails.
SkillMIT★ 7No key
Self-hosted, multi-zone MCP server platform for GKE, EKS and AKS. A git repo of Python tools becomes canary-deployed, autoscaled Rust + Python workers with NeMo guardrails per tool, Entra ID / Google
Hosted by authorBSD-3-Clause★ 3Few starsNo key
🦀⚡ Community skill pack & CLI for Genspark Claw, OpenClaw & Hermes agents — 5 production-ready SKILL.md skills (deep research, reports, slides, browser automation, AI call prep), zero-dependency Node
Node.jsMIT★ 368No key
Blawgy MCP server: research keywords, plan, write, update and publish SEO blog posts from any AI agent
Hosted by authorMIT★ 3Few starsNo key
🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + C
PythonMIT★ 377No key
Zero-dependency System One decision harness: 5 semantic gates saving frontier AI agent tokens on trivial errors & doom loops. Python + TypeScript + Rust. MCP-compatible.
PythonMIT★ 12No key
Lightweight, local-first Python DAG workflow compiler and execution engine with human-in-the-loop checkpoints for CLI and AI-agent workflows.
OfficialPythonApache-2.0★ 14No key
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o
PythonMIT★ 48No key
Recipes for trusting your coding agents: verification, skills, and agent-friendly architecture — baked and ready to serve.
SkillMIT★ 4Few starsNo key
Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
SkillMIT★ 144No key
Build production-grade enterprise agents in minutes, not days, weeks, or months
Node.jsApache-2.0★ 3Few starsNo key
Open-source MCP server that lets AI agents trade Polymarket, with spending limits and a pre-trade check. Your keys stay on your machine.
PythonMIT★ 1Few starsNo key
Set up and manage self-hosted GitHub Actions runners on Linux and Windows, in WSL or Docker
SkillMIT★ 22No key
HMAC-signed zero-width invisible canary token generator and output response leak auditor for LLM guardrails
MCPLink only★ 7
Agent skill for designing, building, testing, and tuning bounded JEV decision layers
SkillMIT★ 32No key
Fast, agent-native policy and approval engine: deterministic CEL policy plus signed, single-use human approvals for AI agent actions.
GoApache-2.0★ 4Few starsNo key
Overwing MCP server: guardrails for LLM output. pass / fail / review verdicts with calibrated confidence for any MCP-capable agent.
Node.jsMITFew starsNo key
Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.
PythonApache-2.0★ 21No key
Rewind any AI agent to point zero. Flight recorder and time machine for coding agents.
Node.jsApache-2.0Few starsNo key
Guardrails for AI coding agents: run Claude Code, Codex, Gemini CLI, Cursor or Copilot unattended and come back to a reviewed pull request. Implement, review and QA agents, a guard on protected paths,
SkillMIT★ 12No key
Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. jev-gate: a strict second lock, 0 of 12 dangerous test comman
PythonMIT★ 10No key
An open-source Agent Skill and CLI tool for managing and formatting documentation in Outline knowledge base
SkillMIT★ 5No key
Who stands behind it
