Operates desktop graphical interfaces like a person, combining hierarchical planning with visual grounding to click through applications and finish multi-step tasks.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- GUI Grounding
Use Agent S to locate on-screen interface elements from a screenshot: ‹what you're looking for›
- Hierarchical Planning
Use Agent S to decompose a computer task into subgoals: ‹what you need›
- Experience Reuse
Use Agent S to store successful interaction traces as reusable experience: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: github.com/simular-ai/Agent-S
Call the API
Auth An API key from Simular AI
Its page: github.com/simular-ai/Agent-S
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APICLI
- Auth
- API Key
- Skills
- 3
Skills
GUI Grounding
Locates on-screen interface elements from a screenshot and maps them to precise click and type coordinates.
Hierarchical Planning
Decomposes a computer task into subgoals and replans when an action produces an unexpected screen state.
Experience Reuse
Stores successful interaction traces as reusable experience so repeated desktop workflows execute more reliably.