FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST.…

Running V2ray inside edge/serverless runtime

A Rust crate for cooking up terminal user interfaces (TUIs) 👨‍🍳🐀 https://ratatui.rs

Universal Rust multiplexer with a typed SDK — drive any CLI or TUI app from code. Native on Linux, macOS, and Windows.

A new kind of language for a new kind of computer

Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required.

Structured skill framework for Claude Code | 128 skills, localhost dashboard with 3-agent orchestration, real-time streaming, MCP tools management, session memory, and project handoffs via markdown…

the runtime your coding agents live on

🔄️ Sync pi.dev agent sessions to SQLite for analytics, uses node:sqlite

The best way to get AI coding agents to solve hard problems in complex codebases.

🦄 ai that works - every tuesday 10 AM PST

A free, open source, and extensible speech-to-text application that works completely offline.

Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.

AI Intelligence CLI - Curated AI insights from Twitter/X Top accounts

Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

Incremental engine for long horizon agents 🌟 Star if you like it!

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

Build, run, and manage agent platforms.

Cli and MCP for gbox. Enable AI agents to operate Android/Browser/Desktop like human.

A conversational system that integrates facial recognition capabilities with large language models. The system remembers the people it interacts with and maintains a conversation history for each r…

Write scalable load tests in plain Python 🚗💨

Maintenance mode — new development in Textual: https://github.com/gonzalezreal/textual

unclutter your .profile

Share code with LLMs via Model Context Protocol or clipboard. Rule-based customization enables easy switching between different tasks (like code review and documentation). Includes smart code outli…

Cost-efficient and pluggable Infrastructure components for GenAI inference

Library for building WebSocket servers and clients in Python

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations