MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
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
Fine-tuned NL-to-SQL specialist served as an MCP tool, benchmarked against prompting Claude directly on accuracy, latency, and cost
MCPLink only★ 1Few stars
Agentic LLM router that sends each request to a LoRA-tuned small model or a larger one by confidence, cutting cost and latency without losing quality. LangGraph, RAG, CNN, Groq and Gemini, with PII an
MCPLink only★ 1Few stars
A self-hosted Autonomous AI Agent Operating System & Workstation (FastAPI + React). Gives local AI agents control over files, projects, storage, documents, LoRA fine-tuning, and hardware.
MCPLink only★ 1Few stars
?? PsycheLink - Mental-Health AI Companion: Intent Classification + Milvus RAG + SSE Streaming + Risk-Alert Closed Loop. Built with Spring Boot 3 / Spring AI.
SkillMIT★ 1Few starsNo key
Local memory layer for AI agents — persistent, searchable memory across sessions without external APIs
PythonMIT★ 1Few starsNo key
Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was f
OfficialSkillMIT★ 40k in collectionNo key
MCP server for multitenant Nixtla TimeGPT forecasting with fine-tuning, rolling backtests, and anomaly detection. HTTP-based JSON-RPC 2.0 API with MongoDB tracking and Vercel deployment.
SkillMITFew 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
Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact',
OfficialSkillApache-2.0★ 256 in collectionNo key
Runnable AI engineering modules: agents, MCP, memory, RAG, voice, fine-tuning, MLOps, and security. One folder per module.
SkillMIT★ 9No key
Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was f
OfficialSkillApache-2.0★ 256 in collectionNo key
Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or
OfficialSkillApache-2.0★ 256 in collectionNo key
Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion). Use when someone asks 'RRF or DBSF?', 'how to combine sparse and dense', 'how to combine scores from multip
OfficialSkillApache-2.0★ 256 in collectionNo key
An agentic AI workflow for SiN waveguide design that bridges modesolverpy, SAX+JAX, and gdsfactory via FastMCP. It handles eigenmode solving and inverse design for GDSII mask output, powered by AWS Be
SkillMIT★ 1Few starsNo key
AI Engineering Specially Topics- Agentic AI & GenAI Explanation
SkillApache-2.0★ 167No key
A small web app + local API for tuning Azure WAF false positives without paying Log Analytics prices.
SkillApache-2.0★ 5No 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
Text to SQL Quickstart with GEPA and RFT
SkillMIT★ 3Few starsNo key
Run a team of AI agents on your own hardware, from the chat app you already use. Any model, local or frontier. They remember, build their own tools, and train the model that replaces them.
PythonMIT★ 1Few starsNo key
Local-first non-linear memory OS for AI operators. One index across Claude Code, Codex, Cursor, Windsurf, Hermes, OpenCode, Aider, pi, and more — with an editable timeline.
Node.jsApache-2.0★ 7No key
Corpus forge syncs a local file system with a SQL database with vector embeddings for storing and serving sovereign AI models.
PythonApache-2.0★ 2Few starsNo key
Production-grade RAG pipeline for accounting professionals — hybrid retrieval (vector + BM25), SSE streaming, multi-user auth, semantic caching, MCP server. FastAPI + Qdrant + Cerebras.
PythonMIT★ 1Few starsNo key
Local code search engine for AI agents: incremental indexer, hybrid retrieval (BM25 + dense embeddings in Qdrant, RSF, per-language reranker) and an MCP server. Tree-sitter chunking, git branch/tag ov
SkillApache-2.0★ 2Few starsNo key
Who stands behind it
