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!

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Cua.kira is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.

Open Vision Agents by Stream. Build Vision Agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

get apikeys for ai hackathons

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

An approach that integrates Transfomer-based attention mechanisms into model predictive control for a learnable control policy.

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

UAV Flight Simulator for Reinforcement Learning Research

Horizontal Robot Arm HTA0

Unofficial implemention of lanenet model for real time lane detection

The program for scheduling recordings and processing of the satellite and ground radio transmissions (like capturing of the weather APT images from NOAA satellites, voice messages from ISS, fixed t…

Apache CouchDB Docker for ARM architecture

The Elastic stack (ELK) powered by Docker and Compose.

A powerful little TUI framework 🏗

The fastai book, published as Jupyter Notebooks

Glances an Eye on your system. A top/htop alternative for GNU/Linux, BSD, Mac OS and Windows operating systems.