MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Local memory layer for AI agents — persistent, searchable memory across sessions without external APIs
PythonMIT★ 1Few starsNo key
Privacy-conscious AI reflection companion concept with visible memory provenance and reviewable next steps.
PythonApache-2.0Few starsNo key
RAG + LLM system for first-pass German contract compliance screening: hybrid BGB/DSGVO retrieval (RRF, cross-encoder reranking), LoRA fine-tuned DistilBERT clause classifier, evidence sufficiency chec
SkillMIT★ 1Few starsNo key
Self-hosted backend for Loopback – Run Coach: workout tracking, Apple Watch training queue, training plans, health metrics, web dashboard, and an MCP server for AI coaching
SkillMIT★ 4Few starsNo key
The retrieval stack matters — but ragweld’s differentiator is the engineering surface area around it: benchmarking, evaluation, diagnosis, and operations. It’s built for senior engineers who need answ
SkillGPL-3.0★ 5No key
36-module AI training curriculum — from zero to local AI sovereignty in 5 phases. Windows .bat scripts, Ollama, Weaviate, MCP. Built for the 800M left behind.
SkillGPL-3.0★ 1Few starsNo key
A simple Go and SQLite MCP server for conversational workout tracking with ChatGPT
GoMIT★ 2Few starsNo key
Local-first opportunity engine that uses Gemma, Unsloth LoRA for shadow training, private memory, offline mobile, and proof tracking to turn effort into proof.
MCPLink only★ 1Few stars
Hands-on training for Finance, Engineering, and Operations teams to manage Snowflake AI spend with a FinOps model. Learn to discover, control, optimize, and govern Cortex AI costs using token usage, c
SkillApache-2.0★ 2Few starsNo key
Epoch AI — AI models database
Hosted by authorMITFew starsNo key
Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'BM25 or sparse vectors?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from
OfficialSkillMIT★ 40k in collectionNo key
A personal running coach that turns your Garmin data into daily briefings, graded workout report cards, and an adaptive training plan — driven entirely through MCP.
PythonMIT★ 3Few starsNo key
Running performance analysis with DuckDB and MotherDuck. Track workouts, training plans, and get science-based insights via Claude Desktop MCP
SkillMIT★ 1Few starsNo key
An example MCP Server to connect a LLM to BigQuery and other databases
MCPLink only★ 2Few stars
Use when working in a project that depends on @prisma/orm-postgres, @prisma/orm-sqlite, or @prisma/orm-mongo (Prisma 8, formerly Prisma Next): editing contract.prisma or a contract.ts builder, running
OfficialSkillApache-2.0★ 48k in collectionNo key
RAG database of the ProleWiki Corpus for enhancing open-source AI agents with a RAG database as encyclopedia of Marxism
PythonAGPL-3.0★ 2Few starsNo key
Stores, retrieves, and manages data as objects in Cloud Storage on Google Cloud (also known colloquially as GCS) buckets. Use when you need to interact with Cloud Storage — set up a Storage MCP server
OfficialSkillApache-2.0★ 21k in collectionNo key
A local training intelligence engine for athletes and AI coaches
SkillMIT★ 7No key
Intent-aware memory for LLM agent.Why every connection exists?, not just that it does.
PythonApache-2.0★ 4Few starsNo key
Give this repo to Claude and it becomes your training coach: real periodized plans, Strava + Apple Health data, progress tracking and grading — files are the database, skills are the features, the age
SkillMITFew starsNo key
Local-first Garmin data warehouse with an analysis-grade MCP server. Sync once, analyze forever - even when the API is down.
PythonMIT★ 9No key
Self-hosted MCP server on your own Garmin data: mirrors Garmin Connect into PostgreSQL, computes training load and muscle freshness, and serves it to Claude, ChatGPT and other clients over stdio or HT
DockerMIT★ 1Few starsNeeds a key
MCP-native workout tracker. Your AI agent (Claude, Cursor, …) writes the program; you lift. Open-source, ~1,500 tests, offline-first PWA, Supabase + RLS.
SkillMITFew starsNo key
Codex skill: personalized weekly training + daily meal plans from body data, goals, diet preferences & equipment — deterministic calorie/macro engine with progress-based adjustments
SkillMIT★ 1Few starsNo key
Who stands behind it
