Skip to content
Fossfits

Vector databases.

Self-hosted stores for embeddings and similarity search. The retrieval layer under RAG, not the chat UI.

Sorted by Most popular

  1. FaissFacebook’s MIT ANN library for billion-scale embedding search on CPU or GPU.MIT · Linux, macOS, +141k
  2. MilvusCloud-native vector database built for large-scale ANN search.Apache 2.0 · Linux, Docker38k
  3. QdrantRust vector database with filters, payloads, and a REST API.Apache 2.0 · Linux, macOS, +226k
  4. ChromaDeveloper-friendly embedding database for local RAG prototypes.Apache 2.0 · Linux, macOS, +223k
  5. pgvectorVector similarity search as a Postgres extension — embeddings without a new database.Other · Linux, macOS, +223k
  6. WeaviateVector database with hybrid search and modular vectorizers.BSD 3-Clause · Linux, Docker15k
  7. txtaiAll-in-one Python framework for embeddings, vector search, and RAG workflows.Apache 2.0 · Linux, macOS, +113k
  8. LanceDBEmbedded serverless vector database — SQLite-style, multimodal, no server to run.Apache 2.0 · Linux, macOS, +111k
  9. postgresmlPostgres with GPUs for ML/AI apps.MIT · Linux6.8k
  10. MarqoDocker-deployed search engine combining vector and keyword search for discovery apps.Apache 2.0 · Linux, macOS, +25k
  11. LongMemoryLocal persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.Apache 2.0 · Linux4.5k
  12. vector-quantize-pytorchVector (and Scalar) Quantization, in PytorchMIT · Linux4k
  13. vault-aiOP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend.MIT · Linux3.4k
  14. trieveAll-in-one platform for search, recommendations, RAG, and analytics offered via APIMIT · Linux2.7k
  15. langchainrbBuild LLM-powered applications in RubyMIT · Linux2k
  16. nocturne_memoryA lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.MIT · Linux1.4k
  17. MemeMeow智能管理表情包MIT · Linux1.3k
  18. WifiForgeWifiForge is a tool developed by Black Hills InfoSec to help train Pentesters on different Wi-Fi attack vectors and Wireless capabilities.Apache 2.0 · Linux, Docker1.2k
  19. catalyst🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.MIT · Linux860
  20. rotary-embedding-torchImplementation of Rotary Embeddings, from the Roformer paper, in PytorchMIT · Linux824

1–20 of 29