Open Source
Open-source projects, licenses and community tooling.
Ultracite v7
Ultracite is designed to help you and your AI models write consistent and type-safe code without the hassle of configuration. Trusted by top companies like Vercel, Clerk, and ElevenLabs. Get started in seconds. npx ultracite@latest init
Open Source
Qwen-Image-2512
Qwen-Image-2512 is the new open-source SOTA for text-to-image generation. It delivers drastically improved photorealism, finer natural details, and superior text rendering.
Open Source
Chatterbox Turbo
Chatterbox Turbo is a 350M parameter open-source TTS model. It features paralinguistic tags (control laughs, sighs, etc.), zero-shot cloning, and runs 6x faster than real-time. Uniquely includes built-in PerTh watermarking for safety.
Open Source
GitHub Wrapped 2025
Your Year in Code 2025 - View your GitHub contributions, stats, and coding journey for 2025.
Open Source
Giselle
Built to design and run AI workflows that actually complete. Zero infra setup—just build and run. Handle complex, long-running tasks with a visual node editor and real-time tracking. Combine models from multiple providers in one canvas.
Open Source
HMPL
HMPL.js provides the flexibility to build server-driven templates with minimal JavaScript. With its block-based syntax, customizable fetch requests, and built-in support for forms, events, and time-based syncing you can deliver dynamic user interfaces without relying on a heavy framework. HMPL integrates with JSON5 for expressive object syntax and DOMPurify for safe HTML rendering, all in just a few kilobytes.
Open Source
ScreenREC
🎬 ScreenREC: The simplest screen recorder ever Record screen, webcam & audio in-browser—no downloads, no signups. Why teams love ScreenREC: ✨ Zero install, works instantly 🔒 Privacy-first, recordings stay local 🎥 Full HD quality ⚡ One-click start 🎨 Dark mode UI 💾 Export MP4/WebM 🌐 100% open source Perfect for tutorials, demos, bug reports, presentations & async team communication. No bloat. No tracking. Just recording done right.
Open Source
A2UI
A2UI is an open protocol by Google enabling agents to generate rich, interactive UIs. Instead of risky code execution, agents send declarative JSON that clients render natively (Flutter/Web/Mobile). Secure, framework-agnostic, and designed for LLMs.
Open Source
Qwen-Image-Layered
Qwen-Image-Layered decomposes images into transparent RGBA layers, unlocking inherent editability. You can move, resize, or delete objects without artifacts. Supports recursive decomposition and variable layer counts.
Open Source
GetProfile
Self-hosted and open-source user profiles and long-term memory for your AI agents. Unlike generic memory solutions that store blobs of text, GetProfile extracts natural language summary, typed traits with confidence scores and relevant memories with importance levels into a structured user profiles stored in your own PostgreSQL database.
Open Source
MiMo-V2-Flash
MiMo-V2-Flash is a 309B MoE (15B active) model by Xiaomi. It is a powerful, efficient, and ultra-fast foundation language model that particularly excels in reasoning, coding, and agentic scenarios, while also serving as an excellent general-purpose assistant for everyday tasks.
Open Source
GitStory
Every commit tells a story. GitStory turns your GitHub activity into a cinematic, shareable timeline — perfect for developers who want to visualize their journey beyond graphs.
Open Source