3D gaussian splatting in CUDA and C++

My personal favorite skills

3D Reconstruction for all

Open-source MCP to use Blender with any LLM

Nano vLLM

A Modular Framework for 3D Gaussian Splatting and Beyond

[CVPR 2025 - Highlight] Original implementation of "3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes"

Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

Some awesome prompts for Jules Agent

State Estimation through Robust Perception in Extreme and Novel Terrains

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

A lightweight finite element toolbox in Julia for education, research, and rapid prototyping of weak-form formulations.

EasyFEA is a user-friendly Python library that simplifies finite element analysis.

Finite element solver for partial differential equations on arbitrary meshes

DUSt3R + Gaussian Splatting

KinectFusion implemented in Python with PyTorch

A breakdown of knowledge graph RAG with diagrams and examples

Immutable mesh processing library

A live stream development of RL tunning for LLM agents

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

No fortress, purely open ground. OpenManus is Coming.

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux.

The Research Agent is an automated research assistant that leverages web search, content extraction, and language model processing to generate comprehensive research reports. It is designed to hand…

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

Fully local web research and report writing assistant

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & En…

Local LLM Powered Recursive Search & Smart Knowledge Explorer

A course on aligning smol models.

🤗 smolagents: a barebones library for agents that think in code.