Stars
A binary and file access authorization system for macOS.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Agent Engineering course files
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
Pydoll is a library for automating chromium-based browsers without a WebDriver, offering realistic interactions.
verl: Volcano Engine Reinforcement Learning for LLMs
j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
A cache for AI agents to learn and replay complex behaviors.
⚙️ Create and run workflows (RPA 2.0)
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
MarinaBox is a toolkit for creating and managing secure, isolated environments for AI agents
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
Open source interpretability artefacts for R1.
Official Repo for InSTA: Towards Internet-Scale Training For Agents
The best way to get AI coding agents to solve hard problems in complex codebases.
🦄 ai that works - every tuesday 10 AM PST
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
Pack your repo into an AI-friendly format and apply AI suggested changes back with ease, all from your terminal.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Lightweight coding agent that runs in your terminal
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
Challenges for general-purpose web-browsing AI agents
A mini, open-weights, version of our Proxy assistant.
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.