Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
AI-powered automated E2E testing. Just enter a URL — AI generates and runs test scenarios.
PythonAGPL-3.0★ 7No key
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
PythonAGPL-3.0★ 7.9kNo key
Claude Code skill that builds autonomous, goal-driven work loops: review, build, fix, audit+patch, and scheduled recurring loops with a Claude Council second-opinion layer.
SkillGPL-3.0Few starsNo key
The loop never sleeps — you finally can. Agents automate the entire development lifecycle (write, review, merge, learn) end to end, with a published safety record. Self-host today; rentable hosted loo
SkillAGPL-3.0★ 21No key
ESP32-family flasher in Rust with structured NDJSON observability for CI/CD and LLM feedback loops — a faithful esptool port plus a final-report file, diagnostic hint engine, and stable exit codes
SkillGPL-2.0★ 5No key
AI coding agent runtime that makes LLMs understand your codebase with repository-aware context, memory, and continuous learning
SkillGPL-3.0★ 6No key
AI-powered E2E testing Agent Skill — self-healing DevQA loop for Claude Code, Codex, Cursor, and 11+ AI coding tools
PythonAGPL-3.0★ 1Few starsNo key
Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing, and real-time threat detection.
Node.jsAGPL-3.0★ 21No key
Enterprise-grade security validation and testing tool for MCP servers. Features 60+ OWASP security rules, schema-aware fuzzing engine, real-time threat detection gateway, and multi-provider LLM analys
Node.jsAGPL-3.0Few starsNo key
A Claude Code skill: an orchestration playbook for driving many coding agents through a large multi-PR engagement.
SkillAGPL-3.0★ 3Few starsNo key
Node.jsAGPL-3.0★ 5No key
Diff-aware security scanner for GitHub PRs — flags mutable Express/NestJS/Next.js routes with no auth middleware and responses leaking sensitive fields. Deterministic, AST-based, human-in-the-loop.
SkillAGPL-3.0★ 1Few starsNo key
AI-native local video timeline editor — AI edits via MCP while you watch in the browser
SkillAGPL-3.0★ 2Few starsNo key
XYZ Forge is a local-first engineering operations system. It coordinates several AI coding agents — Claude Code, Codex, agy (Google's Antigravity CLI), and others — working on the same repositories, a
SkillAGPL-3.0★ 5No key
Code intelligence via tree-sitter — symbols, calls, deps, blast radius, hotspots, dead code, co-change analysis. SQLite, MCP server
SkillAGPL-3.0Few starsNo key
Local code review. Built for human-in-the-loop agentic teams.
SkillGPL-3.0★ 5No key
Compiler-accurate Java analysis & refactoring for AI agents — JDT-backed MCP server: parity-gated reversible refactoring, whole-workspace scope, grounded memory, agent enforcement. No Eclipse required
SkillAGPL-3.0★ 1Few starsNo key
Local-first AI Operating Intelligence for Windows — ReAct agent loop, 50+ tools across 15 categories, zero-code Markdown skills framework, and a Hooks→Permissions→Approval safety gate. 100% on-device
PythonGPL-3.0Few starsNo key
Helps autonomous AI coding agents build projects more reliably — audited phases, real sandboxed tests, anti-mockup validators, MCP-native, tool-agnostic. AGPL-3.0 + commercial dual license.
SkillAGPL-3.0Few starsNo key
Documentation engine for human-AI collaborative system analysis, design and implementation
SkillAGPL-3.0★ 2Few starsNo key
Agent skill to automate pull request review loops using Oracle
SkillAGPL-3.0★ 1Few starsNo key
AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions & skills before you clone — plus an always-on AI attack-signature scanner and native Rust
PythonAGPL-3.0★ 1.0kNo key
A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.
SkillGPL-3.0★ 1.6kNo key
Who stands behind it