Video
flowblade
Video Editor for Linux
★ 3.1k starsGPL-3.0
View guide →// ai-3d · Visionary-Laboratory/visionary
visionary
visionary is an open-source ai 3d project by Visionary-Laboratory (Visionary-Laboratory/visionary on GitHub). It has 526 GitHub stars and 35 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 26 June 2026.
Run visionary locally: the world model carrier built on webgpu-powered gaussia.
💎 Hidden gem★ 526 stars⑂ 35 forksApache-2.0updated 2026-06
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- Visionary-Laboratory/visionary
- GitHub stars
- 526
- Forks
- 35
- License
- Apache-2.0
- Last updated on GitHub
- 26 June 2026
- Category
- AI 3D
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Clone the repository
Fetch the source code onto your machine.
- Install dependencies
Set up the Python environment the project needs.
- Configure the project
Copy the sample config or env file and adjust it.
- Run it
Start the app from the source directory.
// features
Why people love it
3Dgs
Built around 3dgs for a focused workflow.
4Dgs
Built around 4dgs for a focused workflow.
Avatar
Built around avatar for a focused workflow.
Computer Graphics
Built around computer graphics for a focused workflow.
Open source
Inspect, fork, and modify every line of the code.
Self-hosted
Run it on your own machine — no account lock-in.
Advertisement
// run it
Run it yourself
- Clone
Get the source on your machine.
git clone https://github.com/Visionary-Laboratory/visionary.git - Install
Set up Python dependencies.
cd visionary && pip install -r requirements.txt - Start
Launch the application.
cd visionary && python main.py
// use cases
What you can build
- Prototyping ideas quickly from working code
- Integrating into a larger personal stack
- Teaching or studying ai 3d patterns
- Forking and customizing for your own needs
Advertisement
// faq
Questions, answered
What does visionary do?
It the World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform, giving you a working starting point you can run and adapt.
Is visionary free to use?
Yes — the code is open-source, so you can use and modify it without a license fee.
How do I install visionary?
Clone the GitHub repository and follow the README; the typical flow is install dependencies, configure, and run.
What is visionary written in?
It is primarily written in Python, so you will need that toolchain to build or extend it.
Where can I get help with visionary?
The GitHub repository is the hub: open issues for bugs and check the README and discussions for guidance.
// keep exploring
Similar tools
Automation
iflow-cli
iFlow cli is a comprehensive command-line intelligence that embeds in your terminal, analyzes your repositories, does coding tasks, interprets your needs acr…
★ 5.1k starsUnknown
View guide →AI Agents
obsidian-wiki
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
★ 3.5k starsMIT
View guide →AI 3D
HunyuanWorld-1.0
Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model
★ 2.9k starsUnknown
View guide →AI 3D
LongSplat
Run longsplat locally: [iccv 2025] longsplat: robust unposed 3d gaussian splat.
★ 811 starsNOASSERTION
View guide →AI 3D
build-world
Build interactive 3D worlds with your AI agent and Thrixel assets.
★ 95 starsApache-2.0
View guide →// alternatives
Alternatives in AI 3D
The most-starred other AI 3D projects in the LibreAI catalogue — the realistic shortlist if visionary is not the right fit.
- mcp-for-blender★ 30.2k
Control Blender with natural language: an MCP plugin that lets any LLM model, light and animate in 3D
- editor★ 24.7k
Pascal Editor: an open-source 3D architectural editor with MCP tools for humans and AI agents
- text-to-cad★ 18.4k
Give your AI agent CAD superpowers - generate real STEP/STL models from text
- img2threejs★ 17.7k
Turn a reference image into a procedural, animation-ready Three.js model - as code
- Hunyuan3D-2★ 15.0k
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
// more in ai-3d
More in AI 3D
Nearby AI 3D projects in the catalogue, closest in stars to visionary — keep exploring the shelf either side of it.
- MILo★ 528
Mesh-in-the-loop Gaussian Splatting from a SIGGRAPH Asia paper.
- Reall3dViewer★ 514
3D Gaussian Splatting viewer built on Three.js — mark, measure and render with preset LODs.
- GS-SDF★ 535
LiDAR-augmented Gaussian Splatting plus neural SDF, in real time.
- vk_gaussian_splatting★ 504
Vulkan viewer rendering 3D Gaussians via rasterization and raytracing.
- DiffSplat★ 546
DiffSplat, in Python — built for [iclr 2025] official implementation of "diffsplat: repu.
- Embodied-AI-Daily★ 471
A daily-updated collection of arXiv papers on embodied AI: vision-language navigation
Get visionary
Free and open — grab the source, star the repo, and start creating.