Build RL environments for LLM training

A protocol for connecting any editor to any agent

Minimal CLI coding agent by Mistral

Temporal proposals

Our library for RL environments + evals

Executable GenAI prompt templates

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

The official Python SDK for Eval Protocol

slime is an LLM post-training framework for RL Scaling.

Efficient few-shot learning with Sentence Transformers

The official Python SDK for Model Context Protocol servers and clients

The best ChatGPT that $100 can buy.

NanoGPT (124M) in 3 minutes

Securely synchronize files with your devices on iOS using Syncthing

Public repository for Agent Skills

High-performance MinHash implementation in Rust with Python bindings for efficient similarity estimation and deduplication of large datasets

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

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

An inky color scheme for prose and code.

Pretraining data reconstruction scripts for Apertus

Context files in no time for your github repo

The open source coding agent.

Undetected version of the Playwright testing and automation library.

Intuitive, easy CLIs based on python type hints.

Llama from scratch, or How to implement a paper without crying

Easy installer for Claude Code OAuth workflows - Set up @claude mentions in your GitHub repos

🖱️ Generate human-like mouse movements with puppeteer or on any 2D plane