embeddings

thedotmack/claude-mem

A shared memory layer so AI coding agents remember past sessions — claude-mem captures what an AI agent does in a session, compresses it with AI, and re-injects relevant context into future sessions using ChromaDB/SQLite embeddings. It's built as a plugin for Claude Code, OpenClaw, Codex, Gemini, Copilot and others, aiming to give every agent persistent, cross-session memory.

supabase/supabase

An open-source Firebase alternative built entirely on Postgres — Supabase bundles a hosted Postgres database with auth, auto-generated REST/GraphQL APIs, realtime subscriptions, edge functions, file storage, and an AI/vector toolkit. It suits developers wanting Firebase-style convenience without leaving the Postgres ecosystem, using open-source enterprise tools instead of a proprietary backend.

Tencent/WeKnora

Tencent's Go-based platform turns documents into RAG, agents and wikis — WeKnora is a Tencent open-source framework that converts raw documents into a queryable knowledge base, combining RAG retrieval, an autonomous reasoning agent, and a self-updating wiki. It ships with Chrome extension and WeChat Dialog integrations, aimed at teams building Q&A chatbots and internal knowledge tools.

RyanCodrai/turbovec

TurboQuant-based vector index that beats FAISS on speed and size — turbovec compresses embeddings to 2-4 bits using Google Research's TurboQuant and searches the compressed form with SIMD kernels, claiming 4.4x FAISS FastScan speed and up to 15.5x smaller memory at matching recall. No training or rebuild step is needed, making it suited for RAG and agent systems needing online, in-process ANN search from Python or Rust.

neuml/txtai

A Single Framework Combining Vector Search, Graphs and LLM Agents — txtai bundles vector indexes, graph networks and relational databases into one embeddings database that powers semantic search, RAG and multi-model workflows. Rather than stitching together separate vector DB, graph and LLM tools, developers get a unified foundation for building autonomous agents and search-driven AI applications in Python.

apache/seatunnel

SeaTunnel extends data integration to multimodal and LLM workloads — Apache SeaTunnel syncs huge data volumes across 160+ connectors, now covering video, images, and unstructured text alongside structured data for embeddings and LLM pipelines. It runs on Zeta, Flink, or Spark engines, supporting batch, streaming, and CDC with a distributed snapshot algorithm for consistency. Useful for teams needing flexible, multi-engine data pipelines.

ARahim3/DigUp

Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.

Marker-Inc-Korea/AutoRAG

AutoRAG Reborn as a Personal Librarian Agent for Your Files — AutoRAG has pivoted from a Python RAG pipeline-optimization tool into AutoRAG 2.0, a TypeScript agent that acts as a personal librarian: it searches your computer, organizes files, and remembers key info on request. The original AutoRAG continues in the legacy/ folder with maintenance releases via PyPI, so existing RAG-pipeline users aren't stranded.

huggingface/text-embeddings-inference

A blazing fast inference solution for text embeddings models

yoanbernabeu/grepai

Semantic Search & Call Graphs for AI Agents (100% Local)