Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.
A fully modular RAG system with MCP protocol integration, enabling hybrid retrieval, multimodal support, and dual-mode transport for connecting to AI assistants like GitHub Copilot and Claude Desktop.
A self-organizing, persistent semantic memory layer that enables AI agents to store, categorize, and retrieve information using hybrid vector and keyword search. It features autonomous chunking, deduplication, and hierarchical taxonomy management through a PostgreSQL-backed MCP server.
Persistent, semantically-searchable memory for AI agents using local PostgreSQL, pgvector, and Ollama embeddings, exposed via MCP with hybrid retrieval, knowledge graph, and auto-recall hook.
A local MCP server enabling hybrid search over documents, memory, and knowledge graphs for retrieval-augmented generation, with tools for SQLite, semantic memory, and entity-relationship queries.
Cross-tool AI memory engine providing 25 MCP tools for semantic memory, session guard, trace auditing, and proactive IDE interception, all locally without API keys.