Search awesome repositories

A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.

Build LLM-powered applications in Ruby

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

JVector: the most advanced embedded vector search engine

MemFree - Hybrid AI Search Engine & AI Page Generator

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a conceptual fork of OrientDB, the first Multi-Model DBMS. ArcadeDB supports Vector Embeddings.

A high performance Vector Database leveraging parallel graph computing

A Python vector database you just need - no more, no less.

Fast DuckDB-powered TypeScript library for tabular, geospatial, vector, AI, Google Sheets, and data visualization workflows on Deno, Node.js, and Bun.

Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.

Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.

Fast similarity search using DuckDB

Persistent memory for AI coding agents. Local-first, cross-session context, global knowledge, and optional autonomous task execution.

CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.

Lossless storage and search for AI agent sessions, across every agentic client.

Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

Open-source, self-hosted knowledge backend for AI agents — hybrid search (vector + keyword), MCP server, 5 connectors, Docker-ready

One memory, every terminal — a shared memory layer for any MCP client.

Self-hosted MCP server for AI agent memory — 14 core tools, profile-based tiering (86+ available). 88.2% LoCoMo. Works with Claude, Cursor, Windsurf.

MCP server that adds RAG-powered AI chat to any website. One command from Claude Code. Local vector store, multi-provider LLM (OpenAI/Anthropic/Gemini). Zero cloud dependency.

Pure-Zig ANN — Flat, HNSW, IVFFlat, IVFPQ; L2/cosine/inner-product across all families; SIMD @Vector kernels, multi-threaded batch search. 16.94× memory compression on IVFPQ. 76 tests. No C/C++ dependency.