Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a querya…

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

Light, fluffy, and always free - The AWS Local Emulator alternative

Skills for Real Engineers. Straight from my .claude directory.

Build, run and scale AI agents like API and microservices - observable,auditable and identity-aware from day one.

TTS with kokoro and onnx runtime

A minimal on-device voice agent loop

Human — autonomous AI agent runtime in C11. Minimal binary, zero dependencies, 50+ providers, 34 channels, 67+ tools.

Turn complex codebases into clear, navigable architecture diagrams with Claude Code.

The missing tiktoken training code

AI agents running research on single-GPU nanochat training automatically

SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration

Designer Skills Collection: agentic skills, commands, and plugins for design — from research to systems, UI, interaction, and delivery.

The open-source app everyone uses to manage agents at work

Build ultra fast, tiny, and cross-platform desktop apps with Typescript.

A pixel office for your OpenClaw: turn invisible work states into a cozy little space with characters, daily notes, and guest agents. Code under MIT; art assets for non-commercial learning only.

Kanban board for managing Claude Code agents in tmux

Pixel office.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Modern audio compression for the internet.

A nearly-live implementation of OpenAI's Whisper.

✨✨[NeurIPS 2025] VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model

GLM-OCR: Accurate × Fast × Comprehensive

A fast multimodal LLM for real-time voice

OCR & Document Extraction using vision models

Get a parallel build of Claude code that unlocks feature-flagged capabilities like swarm mode.

Enable Claude Code to learn in real-time, update it's knowledge, and grow with you, using supermemory.

Experimental new browser engine

The source code for the Autonomy framework and command. This SDK is what you use to build agents and applications that you can deploy to the Autonomy platform.