MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
OpenAPI spec in, chaos test harness out: WireMock stubs, contract tests and failure scenarios from a team of local LLM agents.
PythonMIT★ 2Few starsNo key
Chaos engineering for MCP agents: a stdio proxy that injects timeouts, errors, malformed JSON, schema drift and stale results, plus a benchmark that measures how agents recover.
PythonMITFew starsNo key
Shared memory, focused engineering practices and reliable handoffs for coding agents. Give your agent one setup prompt.
SkillMIT★ 5No key
Plateforme Agentique MLOps & SRE pour une Gouvernance déterministe d'agents LLM — — — — — — — — Production-Hardened, Platform-Agnostic MLOps & SRE Agentic Control Plane. Features Fail-Closed Policy En
PythonMITFew starsNo key
Persistent feature delivery controller, workflow contracts, and orchestration skills
SkillLink only★ 2Few stars
Official release for paper "Agentic Data Engineering for LLMs: System Design and a Controlled Empirical Study".
SkillMIT★ 3Few starsNo key
100 free AI skills for systems engineers: ECSS reviews, requirement flowdown, interfaces, budgets, verification and design reviews. Local MCP tools included.
PythonMIT★ 11No key
Claude Code skills for engineering managers that compute from exported GitHub data: a stuck-PR and review-queue digest, an iteration report with cycle time, and a blameless incident postmortem timelin
SkillMITFew starsNo key
Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos.
PythonMIT★ 8.6kNo key
AgentEng: Agent Engineering HQ - CLI, MCP, A2A and Agent Engineering for AgentEng HQ events
PythonApache-2.0Few starsNo key
Scan a codebase for decision points where JEV might help, offline and read-only, and test them with evidence
SkillMIT★ 1Few starsNo key
Charter packs, served over MCP: the runtime behind R28's MCP servers. The SDK is r28ai/charter.
PythonApache-2.0Few starsNo key
Claude Code skill + Python CLI: test duplicate, reordered, concurrent and timeout-after-write webhooks against real side effects. Local-first, CI-ready.
SkillMITFew starsNo key
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the
PythonMIT★ 1.0kNo key
Open Lakehouse Compute Fabric: an open-source lakehouse platform with Microsoft Fabric Compute Extension.
PythonApache-2.0★ 276No key
Universal multimodal reverse-engineering engine for AI agents & developers. Transcribe media (YouTube, TikTok, Instagram, podcasts) into structured Markdown, native CC/Whisper, visual frame timelines,
SkillMIT★ 4Few starsNo key
Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.
PythonMIT★ 236No key
Plugin-First Offensive Security & Reverse Engineering Harness for Oh My Pi (OMP)
PythonMIT★ 2Few starsNo key
Memory for coding agents. Reverie keeps the engineering conclusions your agent reaches, reviewed by you, grounded in your code and revised as evidence changes, in one local SQLite file. An MCP server:
PythonApache-2.0Few starsNo key
One MCP & Runtime for Computer-Use (CUA), REA reverse engineering, multi-agent swarm orchestration, and Android companion.
PythonMIT★ 1Few starsNo key
The Deterministic Zero-Trust & Evidence Engine for AI Agents & MCP
PythonApache-2.0★ 1Few starsNo key
Local reverse engineering for humans and AI agents. Built-in x86/x64/ARM64 decompiler, PE/ELF/Mach-O, .NET IL and a compact 12-tool MCP server. Python · MIT.
PythonMIT★ 1Few starsNo key
AI-KIT is a practical starter kit for development: ChatGPT/Codex, Claude, DeepSeek, KIMI, and other coding agents. It provides reusable project context, rules for each stack, adaptive model routing, c
SkillMIT★ 49No key
Inspectable AI agent memory, context engineering and multi-agent orchestration with an MCP server and logical-fleet benchmarks
PythonApache-2.0★ 1Few starsNo key
Who stands behind it
