Open Source AI Projects
Discover 276 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.
276 repositories · updated October 4, 2026
ai-samples: Learn AI Development Patterns for .NET
.NET code samples show how to integrate AI services, build chat experiences, call functions, and evaluate model responses. The repository is archived, so use it as a reference and follow the current .NET AI documentation for maintained guidance.
Zero: Self-Host an AI-Powered Email App
Zero is a self-hostable email app that connects services such as Gmail and Outlook in a unified inbox. It combines email workflows with AI agents and is aimed at people who want more control over their email setup and data.
smolvlm-realtime-webcam: Analyze Webcam Video with SmolVLM
A browser-based demo sends webcam frames to a llama.cpp server running SmolVLM 500M for real-time visual analysis. It suits developers exploring local vision models and webcam workflows, with performance depending on the model server and hardware.
tolgee-platform: Manage Software Localization and Translations
Tolgee is a web-based localization platform for developers and translation teams. It brings in-context editing, translation workflows, SDK integrations, and machine-assisted suggestions together for projects that need to manage translations across languages.
presentation-ai: Generate and Edit AI-Powered Presentations
ALLWEONE Presentation AI creates customizable slide decks from a topic, with an editable outline and live generation. It suits people who want to build, edit, present, or export presentations in a web app.
quarkus-langchain4j-workshop: Learn to Build AI Apps with Quarkus
A hands-on workshop for learning how to build AI-infused applications with Quarkus and LangChain4j. Its step-by-step docs and runnable final states suit developers exploring Java-based AI application development.
memvid: Store Persistent AI Memory in a Single File
Memvid is a Rust-based memory layer that stores content, search indexes, and metadata in a portable .mv2 file. It suits developers building agents that need local, persistent retrieval without operating a separate database service.
repomix: Pack Codebases for AI Analysis
Repomix combines repository files into a structured, AI-friendly output for code review, exploration, and other LLM workflows. Use it from the CLI, website, or as an MCP server, with controls for file selection and token usage.
harbor: Run a Preconfigured Local AI Stack
Harbor is a CLI and companion app for starting connected local LLM services with Docker Compose. It suits people experimenting with models and AI tools who want a shared setup without wiring each service by hand.
inbox-zero: Organize Email with an AI Assistant
Inbox Zero is an email assistant that helps individuals and teams handle busy inboxes with AI-drafted replies, rules, and follow-up tools. Use the hosted app or self-host it when you want more control over setup and configuration.
llamacoder: Generate Small Apps from a Prompt
Llama Coder turns a natural-language prompt into a small app, with an in-browser preview. It suits developers exploring prompt-driven app generation or adapting the project to build their own AI coding experience.
SurfSense: Create Source-Grounded Briefings from Local Documents
SurfSense is a desktop research assistant that indexes documents on your machine, answers questions with citations, and generates study and work materials. It suits users who need document analysis without uploading their files to a hosted service.