MCP servers and skills: search, filter by where they run, and compare.
Graph RAG on SQLite for AI agents: vector retrieval + hand-curated wikilink graph + cross-encoder rerank, with a zero-token per-turn memory ledger. Working pilot.
PythonMIT★ 9No key
Persistent memory for AI agents. Claude Code and Codex share one memory per project. Store, retrieve, summarize, and prune on SQLite, Postgres, Redis, MongoDB, vector databases, and more.
Node.jsMITFew starsNo key
Nordic financial data MCP server for AI agents — semantic search across 1000+ listed companies in Norway, Sweden, Denmark and Finland
Hosted by authorMITFew starsNo key
Open-source voice AI infrastructure — unified pipeline, RAG, evaluation, replay, handoff. Live: voxforge.brohammad.tech
SkillMIT★ 4Few starsNo key
Durable hybrid memory for AI agents: vector + BM25 + temporal + graph recall, exposed through MCP, HTTP, and Python.
PythonApache-2.0★ 9No key
A fast embedded graph database for AI applications and graph analytics
SkillApache-2.0★ 9No key
Academic-paper knowledge-base MCP server: PDF ingestion (MinerU), Qdrant vector search with reranking, two-phase KB management
PythonMIT★ 5No key
MCP server — 97–99% HTML token reduction via DOM AST extraction. No API key, no Vector DB.
Node.jsMIT★ 2Few starsNo key
Self-hosted long-term memory for AI systems. The LLM proposes, a deterministic pipeline decides.
Node.jsMIT★ 1Few starsNo key
Git-versioned, provenance-grounded knowledge layer extracted from a codebase, served to humans and AI agents via MCP
PythonAGPL-3.0★ 9No key
Self-hosted RAG stack for crawl, scrape, search, ingest, query, and ask workflows with Qdrant, TEI embeddings, Chrome rendering, MCP/CLI/REST, and Gemini synthesis.
SkillAGPL-3.0★ 4Few starsNo key
Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 30 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).
Node.jsMITFew starsNo key
Pull, don't push: exact document sections on demand for LLM agents. MCP server + zero-dependency Python core over SQLite FTS5.
PythonMITFew starsNo key
Your data, domiciled on your device. A private AI stack — vector database, RAG, and local LLM — that runs entirely in the browser. Zero egress, zero third-party processors.
Node.jsMIT★ 9No key
A hands-on LangChain course with 100+ runnable labs — RAG, tools, agents, MCP, structured outputs, and multi-provider LLM support.
SkillMIT★ 9No key
Who stands behind it
