10 actions in 5 pieces of software · ranked by words, meaning and measured trust · 1051 ms
modelrecord150 downloads/month
- robotics
Task: robotics
- robotics
modelrecord60,850 downloads/month
- image-to-video
Task: image-to-video
- image-to-video
MCP serverrecord
- fast_vla_predict_robotwin
Predict a 50-step bimanual action chunk (Aloha-AgileX, RoboTwin 2.0) with Fast-VLA. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns:
- fast_vla_predict_robotwin
- 4vla-mcpfound in code, not yet checkedno passport yet
MCP serversandraschi/vla-mcp
- vla_weights
VLA_WEIGHTS - Hugging Face checkpoint download for Wall-OSS and WALL-WM.
- vla_world_model
VLA_WORLD_MODEL - WALL-WM world action model (event joints, Wan prior).
- show_vla_status_card
Show VLA stack status as an in-chat Prefab card.
- vla_xvla
VLA_XVLA - X-VLA 0.9B flow-matching VLA with PEFT for edge agents (Raspbot/Boomy).
- vla_agentic_workflow
VLA_AGENTIC_WORKFLOW - Multi-step VLA + world-model session planning.
- vla_weights
- 5vla-refinement-loopfound in code, not yet checkedno passport yet
MCP serverk1000dai/vla-refinement-loop
- convert_dataset
Convert a raw rollout dir into a LeRobotDataset reference.
- label_rewards
Reward-label a dataset (Robometer → next.reward).
- convert_dataset
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.