by momodel
Local RAG MCP Server with extended file support (including PPTX)
npm:mcp-local-rag-anything · local package17/wkpublished 8 mo ago
Embeddings and similarity search.
Local RAG MCP Server with extended file support (including PPTX)
MCP server for semantic and lexical search over Obsidian vaults, with a self-built embedding index.
MCP server for domain RAG search — connects to Qdrant + PostgreSQL + Code Search API for hybrid search across Jira, Confluence, Git commits, and server-side code repositories
Neruva MCP -- proprietary memory + grounding substrate for AI assistants (Claude Desktop / Claude Code / any MCP client). Typed Records store, document knowledge graph with exact multi-hop traversal (ownership/relationship tracing), semantic + structural
Resolver for AI agents: a question resolves to where its answer is written, read again every time. No keys, no packages. CLI, MCP server and library.
Mnemosyne MCP: FREE Local Embeddings for Knowledge Graph Memory - No API Keys Required
Sub-150ms Web-to-Markdown Engine & Model Context Protocol (MCP) Server for LLM Context Efficiency & RAG Pipelines.
RuvNet KB-First Application Builder - Build intelligent applications on expert knowledge
CLI and MCP server for TickTick task management
RepoSkein gives your AI coding agent a map of your codebase — so it navigates structure instead of grepping and guessing.
Long-term memory for AI agents: hybrid-searched memories over human-editable markdown notes. 100% local — offline ONNX embeddings, SQLite FTS5, MCP server, REST API, CLI, dashboard. No cloud, no API keys.
The agent itself: routing, memory, session profile, local RAG, and reply-format reasoning for a WhatsApp AI agent. Bring your own model.
Local evidence-only Markdown retrieval MCP
KERNL V2.0 - Persistent Intelligence Layer for AI. Transform Claude from stateless to persistent with 75 tools: crash recovery, semantic search, cross-project learning, system control, and 100% Desktop Commander parity.
MCP server for LanceDB-backed long-term memory with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and memory lifecycle management
Agent memory over the OpenCode session history, served over MCP (stdio). Downloads the CGO-free Go binary for your platform on first run.
Engram — a self-hosted team knowledge wiki with semantic search, served as an MCP server. Propose-and-approve knowledge flow (human gate), shared data with the Engram desktop app.
MCP server exposing GreenNode RAG APIs (knowledge bases, documents, search, ingest) over stdio or streamable HTTP.
MCP server for Dolphin semantic code search - works with Continue.dev, Claude Desktop, and other MCP clients
Persistent memory system for Claude Code. Zero API key. Zero Python. 7 hooks + MCP server + SQLite FTS5 + semantic search + knowledge graph + two-way Obsidian vault.