embeddings

The PDFChat app allows you to chat with your PDF files in natural language.

The best RAG interface yet.

Find, connect, rediscover your notes — a local-first second brain for Obsidian. Semantic search with strong Chinese/CJK, relation graphs and semantic paths for connections you never drew, Hot/Cold rediscovery of forgotten notes. Desktop builds the index; phones and tablets search it. No API keys.

Train an adapter for any embedding model in under a minute

Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.

A context harness for AI agents: all your scattered context — code, memory, docs, databases, SaaS — in one searchable, browsable, file-like interface.

Own your AI memory — import ChatGPT, Claude and Gemini exports, see what each AI knows about you. Checkpoint/restore and cross-model continuity for agents.

Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST API and MCP support for AI clients.

A high-performance AI Gateway written in Rust — call 100+ LLM APIs using OpenAI format

Self-hosted RAG platform for AI document search across GitHub, Notion, Google Drive, local files, and web sources with citations.

InferrLM - On-device AI for iOS & Android

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

Go implementation of @qdrant/fastembed.

(distributed) vector database

Self-hostable RAG platform - document ingestion, embedding, and vector search behind a simple REST API

A decentralized vector database for building vector search applications

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

Ollama负载均衡服务器 | 一款高性能、易配置的开源负载均衡服务器，优化Ollama负载。它能够帮助您提高应用程序的可用性和响应速度，同时确保系统资源的有效利用。

An LLM GUI application; enables you to interact with your files, offering dynamic parameters that can modify response behavior during runtime.

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.