The whole synthesizer in one file of C — 165 KB of wasm on the audio thread. Strudel-compatible, and it does not glitch. Ever.

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

A SQL database in Rust: SQLite-compatible, now also speaking Postgres (experimental). The LLVM of databases.

Using LLMs for iteratively exploring the solution search space at scale.

A type-safe TypeScript SQL query builder

AI watermark remover. CLI and Python library to strip visible and invisible AI watermarks (Gemini / Nano Banana sparkle, SynthID) and provenance metadata (C2PA, EXIF, IPTC) from images.

Professional video editing, right in your browser. Made with Rust, WebGPU, WASM, and Tanstack Start.

📱 Real-time mobile monitor & remote control for Antigravity AI sessions. Mirrors your desktop chat to your phone via Chrome DevTools Protocol (CDP) with sub-100ms snapshots, secure global tunnel ac…

A hacky real-time mobile interface to watch and interact with Antigravity chats while you’re away from your desk.

Vite plugin that reimplements the Next.js API surface — deploy anywhere

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

A framework for building native applications using React

JSONata query and transformation language - http://jsonata.org

MiniMax-M2, a model built for Max coding & agentic workflows.

Multilingual Document Layout Parsing in a Single Vision-Language Model

Code. Art. Together.

Wan2.2-Lightning: Speed up wan2.2 model with distillation

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Pulumi - Infrastructure as Code in any programming language 🚀

Feasible cost konfigurable NAT: An AWS NAT Instance AMI

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.

PostgreSQL vector database extension for building AI applications

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.