Fast audio super resolution from 16khz to 48khz.

This GitHub repo is a powerhouse collection of APIs you can start using immediately to build everything from simple automations to full-scale applications. One of the most valuable API lists on Git…

A high quality and fast TTS repository

Specification and documentation for Agent Skills

End-to-end pipeline converting generative videos (Veo, Sora) to humanoid robot motions

Browser automation

warpsurf: a browser copilot extension

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

Google 💚 MCP

dLLM: Simple Diffusion Language Modeling

An open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare stack

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

Build realtime AI voice agents using FastRTC for low-latency streaming, Superlinked for vector search, Twilio for live phone calls, and Runpod for scalable GPU deployment.

The python library for real-time communication

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

One Place for Agents to Store, Observe, and Learn. Context Data Platform for Self-learning Agents, designed to simplify context engineering and improve agent reliability and task success rates.

Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)

A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

Lightning-fast, on-device TTS — running natively via ONNX.

Valdi is a cross-platform UI framework that delivers native performance without sacrificing developer velocity.

✨ Open-source AI hackers for your apps 👨🏻‍💻