The database of free AI tools on GitHub

Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.

🌐 The Internet Computer! Free, Open-Source, and Self-Hostable.

LocalGPT privately indexes and queries documents with AI.

Your own search engine

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.

A personal librarian agent for organizing files and answering questions.

Hybrid search for dense, sparse, tensor, and full-text data for LLM applications.

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

Unified local-first search tool for humans and AI agents.

Lightweight selfhosted Firefox Send alternative without public upload. AWS S3 supported.

AI search engine with RAG and vector database for self-hosting

AI job intelligence for scraping, ranking, and tailoring job applications.

Sync-in · Sovereign platform for file storage, sharing, synchronization, and collaboration.

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

Implementation of Alphafold 3 from Google Deepmind in Pytorch

All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine

A group of notebooks and other files which can help you learn AI from scratch.

local-first semantic code search engine

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

A local-first AI knowledge base & NotebookLM alternative built with Electron.

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

Rust library for generating vector embeddings and reranking locally!

Clean Xcode, Docker, Homebrew, and developer caches, remove project and AI artifacts, analyze storage, and reclaim disk space from the Terminal.

Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no chan

[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"

On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.

为 Bilibili、YouTube 及本地视频提供 AI 视频摘要和知识库.AI video summarizer and knowledge base for Bilibili, YouTube and local videos.

A fast, multi-threaded Redis® and Valkey alternative written in Rust: drop-in compatible, with full-text and vector search built in

AI pair programming in your terminal — one static binary, sub-ms startup, any model

GraphRAG-rs is a high-performance, state-of-the-art Rust implementation of GraphRAG (Graph-based Retrieval Augmented Generation) that builds knowledge graphs from documents and enables natural languag