Stars
Silero Models: pre-trained text-to-speech models made embarrassingly simple
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Chrome DevTools for coding agents
Desktop app and API created in public for multi-agent Claude Code orchestration - coordinate local and remote agents through @mentions.
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
AI agents running research on single-GPU nanochat training automatically
The AI toolkit for building reliable browser automations
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…
👻 Primitive and flexible state management for React
🤖 Build voice-based LLM agents. Modular + open source.
Observability for contexts. Given a coversation log (messages), this tool will provide a breakdown of its components and their sizes. It also classifies messages into various categories so we can o…
A general purpose scientific writer
Specification and documentation for Agent Skills
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Command line tools for Azure Functions
The official implementation of the W&B Models and Weave MCP server.
Open-source library for scalable, reproducible evaluation of AI models and benchmarks.
[CVPR'22] Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Official Python SDK for Deepgram.
A repository for surgical action triplet dataset. Data are videos of laparoscopic cholecystectomy that have been annotated with <instrument, verb, target> labels for every surgical fine-grained act…
AI that sees your screen, listens to your conversations and tells you what to do
Experience email the way you want with Mail0 – the first open source email app that puts your privacy and safety first. Join the discord: https://mail0.link/discord
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!