Semantic memory for Hermes, stores conversations as embeddings, retrieves by meaning instead of keyword matching. Works with any embedding backend.

ROS2 Control. Hermes Evolving Intelligence. Synchronized. ִֶָ.💖 ࣪ ִֶָ🪽་༘

The agent that grows with you

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

A high throughput low latency shared memory object store specially optimized for RL.

You like pytorch? You like micrograd? You love tinygrad! ❤️

[IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving

The comma.ai Calibration Challenge!

commaVQ is a dataset of compressed driving video

Train transformer language models with reinforcement learning.

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

An index of algorithms for offline reinforcement learning (offline-rl)

Mobile manipulation research tools for roboticists

PyTorch code for the paper "Model-Based Imitation Learning for Urban Driving".

Learning in infinite dimension with neural operators.

This repository contains implementations and illustrative code to accompany DeepMind publications

Solve puzzles. Improve your pytorch.

🐢 Open-Source Evaluation & Testing library for LLM Agents

ROS connector plugin for the SOFA framework.