Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.

Run Claude Code, Codex, and Gemini side by side — each in its own git worktree

Build Real-Time Knowledge Graphs for AI Agents

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

the runtime your coding agents live on

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static bin…

Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.

verl: Volcano Engine Reinforcement Learning for LLMs

FlashMLA: Efficient Multi-head Latent Attention Kernels

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

A Comprehensive Guide for Generative AI, Agentic AI, Multimodal AI, Physical AI Interviews. Proven Formula for multiple FAANG offers and more

Local CLI Copilot, powered by Ollama. 💻🦙

DeepEP: an efficient expert-parallel communication library

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

Automatically identify and highlight key content within PDF files using advanced AI techniques, simplifying the process of reading books and papers.

Visualize any GitHub codebase: free interactive architecture diagrams and one-minute explainer videos. Replace 'hub' with 'diagram' in any GitHub URL.

Body Transformer: Leveraging Robot Embodiment for Policy Learning

LLM training in simple, raw C/CUDA

Learnings and programs related to CUDA

A high-throughput and memory-efficient inference and serving engine for LLMs

LLM inference in C/C++

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

DSPy: The framework for programming—not prompting—language models

Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

You like pytorch? You like micrograd? You love tinygrad! ❤️

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

An Open-Ended Embodied Agent with Large Language Models

A browser extension that enhance search engines with ChatGPT

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Accurate answers and instant citations for your documents.