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!

🙌 OpenHands: AI-Driven Development

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

The official Python SDK for Model Context Protocol servers and clients

Universal memory layer for AI Agents

A modular graph-based Retrieval-Augmented Generation (RAG) system

🧠 Roo Code Memory Bank: Seamless project context in Roo Code. No more repetition, just continuous development!

Web search using free google search (NO API KEYS REQUIRED)

Real-time voice-changer for voice-chat, etc. Will support many different voice-filters and features in the future. 🎵

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

⚡ The Mobile Robot Programming Toolkit (MRPT)

RTAB-Map library and standalone application

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Clone of golang/groupcache with TTL and Item Removal support

[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution

Models I've trained over the years

[ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer

Rate limiting for go-redis

repo for DynamicBind: Predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Personal Website & Blog Theme for Hugo

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

[CVPR 2025 Highlight] DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

The open-source hub to build & deploy GPT/LLM Agents ⚡️

Russian speech technology links

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

PyTorch implementation of Real-ESRGAN model

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

Depth-Aware Video Frame Interpolation (CVPR 2019)