Write HTML. Render video. Built for AI agents.
State-of-the-art multimodal OCR model for complex document understanding with 0.9B parameters
Turn any portrait into a realistic talking head video with just audio input
AI-powered content marketing agent for creators to monetize across global platforms
Web scraping and browser automation library for building AI-ready data pipelines
All-in-one AI desktop companion with VRM models, computer control, and multi-agent collaboration
Code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents
CLI framework for building, testing, and benchmarking AI agent skills across models
AI-powered self-hosted personal finance app with receipt recognition and MCP integration
Self-hosted cloud development environments and AI coding agents with centralized governance
High-performance neural network inference framework optimized for mobile platforms
Control Codex AI coding agent from your iPhone with end-to-end encrypted pairing
AI speech toolkit for Apple Silicon β ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML