MCP servers and skills: search, filter by where they run, and compare.
Multi-perspective code review council for Claude Code. 3 advisors by default, 10 agents in deep mode (Opus + Codex). Evidence chains, adversarial self-test, dual-path verdict. Based on Karpathy's LLM
SkillMIT★ 4Few starsNo key
Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на каком уровне усилий её запускать. Каждый совет со ссылкой на офиц
SkillMIT★ 128No key
Caveman compresses blindly — dense technical text quietly loses meaning. Brevix fixes that: same rule-based brevity, plus a local embedding model that verifies the compressed output still says what th
SkillMIT★ 4Few starsNo key
PythonMITFew starsNo key
MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active tokens and -83% wall time, vs 78.3% plain. Structural code navigation + persistent memory engine. Works with ev
PythonMIT★ 1.2kNo key
Open-source healthcare AI agent skills and life sciences agent skills. 42 skills for medical coding, risk adjustment, claims analytics, quality measures, genomics, imaging, and drug discovery across 1
OfficialSkillMIT-0★ 66No key
CLI, MCP server, and API-compatible interface for Perplexity AI
PythonMIT★ 20No key
What would X do? Turns a person's talks, podcasts and essays into a cited wiki your agent reasons from. Claude Code skill + CLI.
SkillMIT★ 1Few starsNo key
Free open-source AI YouTube Shorts generator and faceless video maker in Python. Any LLM (GPT, Claude, Gemini, Ollama) writes scripts; text-to-speech, stock footage or AI images, word-synced captions,
PythonMIT★ 46No key
Placebo-controlled benchmark of the most-starred coding agent skills
SkillMIT★ 19No key
Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-
PythonMIT★ 60No key
Claude Code plugin and MCP server: a cheap model, DeepSeek V4.1 Flash, reviews Claude's code for bugs and gives second opinions for under a cent each. Claude stays the sheriff.
PythonMITFew starsNeeds a key
Which 5-hour window took you out — and where the money goes. Local profiler for Claude Code, OpenClaw & Hermes Agent: usage windows, burn by source (cron/chats/subagents), the overnight bill, why it b
PythonMIT★ 113No key
Even your AI needs a second opinion. A self-hosted MCP server on Google Cloud Run that lets Claude, ChatGPT, Cursor, and Gemini CLI peer-review their work with a different frontier model — Claude Opus
SkillApache-2.0Few starsNo key
Emotional memory for AI agents — dual-engine mood tracking, behavioral prediction, and governed memory that fades naturally over time. MCP server with 12 tools. Built with Opus 4.6.
PythonMIT★ 1Few starsNo key
Autonomous bug bounty hunting with Claude Agent SDK — 6 specialist AI agents, 19 MCP tools, one command
PythonMITFew starsNo key
The first open-source effort estimation tool built for AI coding agents. PERT + METR + wave planning.
SkillApache-2.0★ 6No key
MCP server for Claude Code that surfaces Ghostty shell integration events
PythonMIT★ 3Few starsNo key
Extract tacit team knowledge from GitHub PRs and CI failures → generate CLAUDE.md and .claude/rules/ files.
PythonMIT★ 4Few starsNo key
Orchestrate a heterogeneous AI software team. Pay junior prices for senior-level output.
PythonMIT★ 1Few starsNo key
MCP server for KiCad — 71 tools for AI-assisted electronics design
PythonMIT★ 27No key
MCP server: delegate Claude Code work to ccr subagents (DeepSeek/etc) so heavy I/O stays out of your Opus context
PythonMITFew starsNo key
Who stands behind it
