Lightweight repo-local hybrid (semantic + keyword) code search over MCP. Pure npm — no Docker, no Ollama, no servers. 11 languages via tree-sitter, jina-code embeddings, LanceDB, live file watcher. One command to install.
MCP server for CodeRAG — exposes codebase search, context, and status tools via Model Context Protocol
Local RAG MCP Server - Easy-to-setup document search with minimal configuration
Phase 2 of the catalog plane. Adds vector embeddings, AI-agent access patterns, and the MCP server scaffolding on top of the Phase 1 foundation in `@voyantjs/catalog`.
The Retrieval-Augmented Generation (RAG) module contains document processing and embedding utilities.
HanaVectorRag vector store (SAP HANA Cloud Vector Engine) and HanaVectorRagProvider for @mcp-abap-adt/llm-agent.
Phase 2.x — MCP (Model Context Protocol) server scaffolding for the catalog plane. Wraps the catalog plane's APIs as agent-callable tools so AI assistants (Claude, ChatGPT plugins, custom agents) connect with tenant-scoped credentials and call tools rathe
A rag component for Convex.
A a collection of languages stemmers and stopwords for Lunr Javascript library
QdrantRag vector store and QdrantRagProvider for @mcp-abap-adt/llm-agent.
PgVectorRag (PostgreSQL + pgvector) and PgVectorRagProvider for @mcp-abap-adt/llm-agent.
Offline HTTP RAG (Retrieval-Augmented Generation) server for the Red Sift Design System — returns ranked, scored documentation chunks for any LLM/agent to consume.
RAG and embedder composition for the SmartAgent runtime.
MCP server for the Red Sift Design System — provides component lookup, prop documentation, and code generation tools for AI assistants.
Model Context Protocol implementation for TypeScript
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati
Core interfaces, types, and lightweight default implementations for LLM agent orchestration.
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).
MCP server that connects AI agents to a configurable RAG Pixels HTTP backend
Mneme — the memory layer for your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.
A TypeScript SSE proxy for MCP servers that use stdio transport.
Orchestrateur universel agents IA multi-modeles via MCP. Inclut le protocole 'Custom-Nickname' pour identifier vos agents avec des surnoms originaux (The Chaos Prophet, Shadow Sniper, etc.), l'isolation mémoire (Private Memory Context) et le support pour
Command-Line Interface for Firebase
Ollama embedding provider and OllamaRag convenience class for @mcp-abap-adt/llm-agent.
No description provided.
No description provided.
No description provided.