Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Spirit-v1.5: A Robotic Foundation Model by Spirit AI
| Date | Stars |
|---|---|
| 2026-07-31 | 631 |
| 2026-08-03 | 631 |
| 2026-08-06 | 631 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> # Spirit-v1.5 <br> <sub>A Robotic Foundation Model by Spirit AI</sub> [](https://www.spirit-ai.com/en/blog/spirit-v1-5)   [](https://huggingface.co/Spirit-AI-robotics/Spirit-v1.5) </div> This repository contains the official implementation of the **Spirit-v1.5 VLA model**, as well as the runtime wrapper required to reproduce our results on the RoboChallenge benchmark.  As of Jan 11, 2026, Spirit-v1.5 ranks **#1** on the [RoboChallenge](https://robochallenge.cn/home) Table30 benchmark. ## 📰 News * **[2026-01]** Initial Release: Technical blog, inference code, base model checkpoint, and a fine-tuned checkpoint are now available. * **[2026-4]** Fine-tuning code released! ## Directory Structure ```text spirit-v1.5/ ├── model/ # Model architecture │ ├── modeling_spirit_vla.py # Main model architecture (Qwen3-VL backbone + DiT head + policy API) │ ├── dataset/ # Dataset and data processing │ ├── dataset.py # Dataset implementation │ └── transforms.py # Data transformations │ ├── utils/ # Utility functions │ ├── checkpoint.py # Checkpoint loading/saving utilities │ ├── distributed.py # Distributed training utilities │ ├── logger.py # Logging utilities │ ├── normalization.py # Data normalization utilities │ ├── sampling.py # Sampling strategies │ ├── tensor_ops.py # Tensor operations │ └── vlm_utils.py # Vision-Language Model utilities │ ├── robochallenge/ # RoboChallenge integration │ ├── run_robochallenge.py # Python entrypoint │ ├── runner/ │ │ ├── executor.py # RoboChallengeExecutor (Checkpoint loading, inference, I/O) │ │ └── task_info.py # Task metadata (robot type, action type, prompts, etc.) │ ├── robot/ # Derived from open-source RoboChallengeInference │ │ ├── interface_client.py # RoboChallenge HTTP client │ │ └── job_worker.py # Job polling loop and execution flow │ └── utils/ # Derived from open-source RoboChallengeInference │ ├── enums.py # Shared enums/constants │ ├── log.py # Logging helpers │ └── util.py # Misc utilities │ ├── scripts/ # Execution scripts │ ├── run_robochallenge.sh # RoboChallenge runtime launcher │ └── run_finetune.sh # Training launcher │ ├── train.py # Main training script ├── requirements-base.txt # Core dependencies (inference only) ├── requirements-train.txt # Additional training dependencies ├── requirements.txt # Complete dependencies (base + training) ├── pyproject.toml # Project configuration with optional dependencies └── README.md # This file ``` ## Installation & Setup ### System Requirements - **Hardware**: Tested on NVIDIA A100 80GB GPU. - **Software**: Python 3.10+. ### Installation Options #### Option 1: uv (recommended) **For inference only:** ```bash uv sync source .venv/bin/activate ``` **For training:** ```bash uv sync --extra train source .venv/bin/activate ``` #### Option 2: pip **For inference only:** ```bash python -m venv .venv source .venv/bin/activate pip install -r requirements-base.txt ``` **For training:** ```bash python -m venv .venv source .venv/bin/activate pip install -r requirements-base.txt pip install -r requirements-train.txt ``` > **Note**: `flash-attn` requires matching CUDA and PyTorch versions. If installation fails, refer to the [flash-attn installation guide](https://github.com/Dao-AILab/flash-attention#installation-and-f
Excerpt of 11,114 characters
Read on GitHub
10
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bf6bd11141e86b5b, llm:Repository name and description: 'Spirit-v1.5: A Robotic Foundation Model by Spirit AI' — indicates a foundation model for robotics (robotic foundation model). Language: Python.
matched fp:bf6bd11141e86b5b, llm:Repository name and description: 'Spirit-v1.5: A Robotic Foundation Model by Spirit AI' — indicates a foundation model for robotics (robotic foundation model). Language: Python.
matched fp:bf6bd11141e86b5b, llm:Repository name and description: 'Spirit-v1.5: A Robotic Foundation Model by Spirit AI' — indicates a foundation model for robotics (robotic foundation model). Language: Python.