Build physical-AI systems that can understand scenes, simulate outcomes, and learn actions.
Search by what you want to achieve. Strong free badges are reserved for tools whose access was actually checked.
548 tools found
Build physical-AI systems that can understand scenes, simulate outcomes, and learn actions.
Turn images or video into depth, camera, and 3D geometry outputs with an open research toolkit.
Evaluate a large open reasoning model for planning, tool calling, and agent workflows.
Build cooperating AI agents with tools, memory, simulations, and repeatable research workflows.
Prompt a live simulated world and watch it evolve instead of waiting for a fixed video clip.
Give an MCP-compatible agent access to ElevenLabs voice, speech, and audio-processing tools.
Let AI shoppers walk through a Shopify theme before you publish it and surface likely conversion friction.
Describe an app idea and get a runnable prototype in a format you can inspect and deploy.
Give an agent a goal and let it plan, inspect files, use tools, and return a deliverable from one workspace.
Generate, edit, and organize campaign-ready visuals across image, video, audio, 3D, and stock in one suite.
Turn text and a permitted reference clip into expressive speech using an open research implementation.
Generate short text-to-video or image-to-video clips with an open model family.
Recraft a reference photo into new scenes while keeping the person recognizable.
Turn a website reference into an editable React starting point that you can run and own.
Generate expressive speech and clone a voice with detailed control over delivery.
Add an AI-enabled rich-text editor to your own web app instead of building the editor from scratch.
Try virtual clothing swaps or pose transfer while keeping the reference person and garment details in view.