#vla Repositories
Discover 23 active open source GitHub repositories tagged with #vla, accumulating 27,475 total stars (averaging 1,194 stars per project). Leading this topic is dexmal/dexbotic with 3,238 stars.
23 repositories total
๐ MindPaw โ An open-source desktop quadruped robot dog based on ESP8266, supporting voice, gesture, web remote control, Doubao AI dialogue, and PAD emotional interaction. Featuring an optional AI Infra gateway, it is ideal for robotics beginners, embedded AI, edge agents, and HRI research.
NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.
InternRobotics' open platform for building generalized navigation foundation models.
A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T-N1.7, FastWAM, Cosmos3, DreamZero, DeepSeek-V4, GLM-5.3, Kimi-K3, and more.
[NeurIPS 2025 spotlight] Official implementation for "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving"
FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B
๐๐๐A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.
This project aims to provide a comprehensive, practical-oriented learning/interview manual in Chinese for algorithm engineers dedicated to entering the VLA (Vision-Language-Action) field. Unlike general CV/NLP interview guides, this project focuses on the unique challenges of Robotics.
Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.
Knowledge base of papers, open-source projects, industry insights, and job-seeking resources on humanoid robot motion intelligence
๐ฅ SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.
[ICLR2026] Official implementation for "JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation"
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
๐ Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
๐ This repository collects papers from arXiv on topics including VLN, VLA, World Models, SLAM, Gaussian Splatting, and nonlinear optimization. It updates automatically every day! The Issues section features the 10 latest papers.
Frequently Asked Questions
What is the most popular #vla repository on GitHub?
The top ranked open source #vla project on GitHub is dexmal/dexbotic with 3,238 stars. Dexbotic: Open-Source Vision-Language-Action Toolbox
Which programming languages are most used in #vla repositories?
Among the top ranked #vla projects on GitHub, the most common programming languages are Python, HTML, C++, Jupyter Notebook.
How is the #vla repository ranking calculated?
We track 23 active open source repositories tagged with #vla (500+ stars), totaling 27,475 stars with an average of 1,194 stars per repository. Rankings update daily from the GitHub API.