Clean, reusable paper implementations for trending papers on alphaXiv

The best ChatGPT that $100 can buy.

Official inference framework for 1-bit LLMs

Supercharge Your LLM Application Evaluations 🚀

🚀 The fast, Pythonic way to build MCP servers and clients.

Set of robotic environments based on PyBullet physics engine and gymnasium.

Textbook on reinforcement learning from human feedback

An extremely fast Python package and project manager, written in Rust.

Lightweight coding agent that runs in your terminal

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

A fully customizable and self-hosted sandboxing solution for AI agent code execution and computer use. It features out-of-the-box support for backtracking, a simple REST API and Python SDK, automat…

verl: Volcano Engine Reinforcement Learning for LLMs

Model Context Protocol Servers

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

Curated list of datasets and tools for post-training.

Democratizing Reinforcement Learning for LLMs

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Sky-T1: Train your own O1 preview model within $450

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

High-resolution models for human tasks.

Download scripts for EPIC-KITCHENS

Run frontier AI locally.

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…