Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONRunAnywhere is a cross-platform SDK suite for running AI models fully on-device across phones, browsers, desktops, and servers. It supports LLMs, vision, speech, voice agents, RAG, embeddings, and image generation with a single semantic API.
AnythingLLM is an all-in-one AI application for building a private, local-first ChatGPT experience with document ingestion and AI agent capabilities.
PixelRAG renders documents as screenshots and retrieves over images directly, preserving visual structure like tables and charts that text parsing loses. Includes a hosted 8.28M-page Wikipedia index, CLI tools, and Claude Code integration.
TARS is a multimodal AI agent stack from ByteDance with two projects: Agent TARS, a CLI and Web UI agent integrating MCP tools and browser control, and UI-TARS Desktop, a native GUI agent app that controls computers via vision-language models.
Jolito is an open-source flashcard app for learning spoken Mexican Spanish: spaced repetition plus audio on prompts and answers, keyboard-first typed recall, offline-first PWA use, and Anki deck import.
Apache SeaTunnel is a high-performance, distributed data integration tool supporting 160+ connectors, batch-stream integration, and multi-engine execution.
MoziAI-35B is a locally deployable open-source multimodal LLM with a 35B MoE architecture compressed to ~15.9 GB via MoziSmartBit quantization, offering 256K context, vision, tool calling, and a finance-focused reasoning framework.
Turbo AI Chat is a native on-device LLM chat application based on HarmonyOS NEXT, designed to verify the complete pipeline for running local LLMs directly on HarmonyOS devices.
LearnNote is a local-first AI learning assistant that transforms videos from Bilibili, YouTube, and local files, as well as PDFs, into structured notes via subtitles or transcription, supporting reading, editing, and exporting in a web workbench.
Deep Lake is a serverless multimodal database for AI that combines vector search with storage for embeddings, images, video, audio, and documents. It streams data directly from cloud storage to PyTorch/TensorFlow, supports versioning, and integrates with LangChain, LlamaIndex, and Weights & Biases.
