Open Source AI Projects
Discover 275 open source AI repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. AI projects here are most often combined with LLM, Python and TypeScript. Last updated October 4, 2026.
275 repositories · updated October 4, 2026
lightclaw: Run a Lightweight Local-First AI Assistant
LightClaw is a Rust-based AI assistant packaged as a single binary, with tools, local memory, and Telegram and Discord interfaces. It suits users who want an agent they can run without a Python runtime or external vector database.
alsoasked-mcp: Search People Also Ask Data with MCP
alsoasked-mcp connects MCP-compatible assistants to the AlsoAsked API for Google People Also Ask research. It suits SEO and content teams that want to explore question hierarchies by search term, language, and region from an assistant workflow.
sniffly: Analyze Claude Code Usage and Errors
Sniffly turns Claude Code logs into a local dashboard for reviewing usage patterns, error types, and message history. It suits developers who want to understand how they use Claude Code or share selected project insights with teammates.
Noi: Organize AI Chats in a Desktop Workspace
Noi is a desktop workspace for bringing AI chat workflows, prompts, and local tools into a more focused browsing setup. It suits people who switch between AI assistants and want separate sessions, reusable prompts, and local-first settings.
autogen: Build Multi-Agent AI Applications
AutoGen is a Python framework for building AI agents that work independently or alongside people. It supports multi-agent orchestration, model and tool integrations, and prototyping, but is now in maintenance mode.
stable-diffusion-webui: Generate Images with Stable Diffusion
A Gradio-based web interface for generating and editing images with Stable Diffusion. It gives artists and other local users a browser-based workflow for prompts, image-to-image tools, model options, and extensions.
genaiscript: Build LLM Workflows with JavaScript
GenAIScript is a JavaScript and TypeScript toolkit for assembling prompts and orchestrating language models, tools, and data. The repository is marked deprecated and archived, so it may suit existing users better than new projects.
upscayl: Enlarge Images with AI
Upscayl is a desktop app for enlarging and enhancing low-resolution images with AI models. It runs on Linux, macOS, and Windows, and is best suited to users with a Vulkan-compatible GPU.
Zero: A Self-Hosted AI Email App
Zero is an open-source email app for managing accounts from providers such as Gmail and Outlook, with AI features and a focus on privacy. It suits people who want a customizable inbox they can self-host.
QueryWeaver: Turn Natural-Language Questions into SQL
QueryWeaver converts plain-English questions into SQL by using a graph representation of database schemas. It suits teams that want a self-hosted Text2SQL web app, REST API, MCP interface, or Python SDK for PostgreSQL and MySQL.
index-tts-lora: Fine-Tune IndexTTS for Custom Voices
A Python project that adds LoRA fine-tuning workflows to IndexTTS for single- and multi-speaker voice synthesis. It is aimed at users who want to adapt speech generation to speaker audio and improve prosody and naturalness.
jan: Run AI Models Locally or Connect to Cloud Models
Jan is a desktop AI assistant for downloading and running language models on your computer, with optional connections to cloud providers. It suits people who want local control and privacy alongside custom assistants and an OpenAI-compatible local API.