Open Source Introductory Systems Programming Textbook for the University of Illinois

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B c…

SGLang is a high-performance serving framework for large language models and multimodal models.

Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.

The open source coding agent.

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt

The best ChatGPT that $100 can buy.

Share your Immich photos and albums in a safe way without exposing your Immich instance to the public.

High performance self-hosted photo and video management solution.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

A comprehensive collection of PyTorch tutorials covering essential concepts and applications

Chaos testing, network emulation, and stress testing tool for containers

The easiest, most secure way to use WireGuard and 2FA.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Web Push library for Java

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

FinRL®: Financial Reinforcement Learning. 🔥

Log in as another user in Rails

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.

An ASCII graph drawing app

Rails plugin that logs/displays a backtrace of all SQL queries executed by Active Record

A simple, fully convolutional model for real-time instance segmentation.

Ruby production code coverage collection and reporting (line of code usage)

A high performance and flexible authorization/permission engine built for developers and inspired by Google Zanzibar

Compile a Node.js project into a single file. Supports TypeScript, binary addons, dynamic requires.

Combine/group together PRs (for example from Dependabot and similar services)