OPEN SOURCE, OPEN TO EVERYONE

Open source. Open possibilities.

Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.

Human-curated · Discover open source3940discovered

A little curiosity. A world of open source.

THE FIRST COLLECTION
Topic: vision清除
pixelragStarTrail-org
ADDED

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.

AI & MLData & databasesRAG & knowledge
ADDED

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.

AI & MLAutomationAI agents
skyvernSkyvern-AI
ADDED

Skyvern automates browser-based workflows using LLMs and computer vision, providing a Playwright-compatible SDK and a no-code builder to replace brittle XPath-based automation.

AutomationAI & MLBrowser & RPA
ADDED

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.

AI & MLAI assistants
librechatdanny-avila
ADDED

LibreChat is a self-hosted, open-source AI chat platform that unifies major AI providers (OpenAI, Anthropic, Google, AWS Bedrock, and OpenAI-compatible endpoints) in one interface, adding Agents, MCP tools, Code Interpreter, artifacts, web search, and multi-user authentication.

AI & MLSelf-hostedAI assistants
ADDED

Xray-core is an open-source network proxy platform from Project X, originating from the XTLS protocol. It supports VLESS, XTLS, REALITY and related transports, with install scripts, Docker images, web panels and many GUI clients across platforms.

Self-hostedDeveloper toolsMonitoring & security