Build, evaluate and train General Multi-Agent Assistance with ease

Chrome DevTools for coding agents

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

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

🤗 smolagents: a barebones library for agents that think in code.

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

Democratizing Reinforcement Learning for LLMs

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

🙌 OpenHands: AI-Driven Development

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A formalization of ML kernel languages

Verified tensor compilation in Lean

A verified tensor library in Lean

Hands-On Practical MLIR Tutorial

A programming framework for agentic AI

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

A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files

Fast and Accurate ML in 3 Lines of Code

🦜🔗 The platform for reliable agents.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

A syntax-highlighting pager for git, diff, grep, and blame output

A terminal workspace with batteries included

how to learn PyTorch and OneFlow

compiler learning resources collect.

Omnivore is a complete, open source read-it-later solution for people who like reading.

Rust bindings for the Z3 solver.

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization