Your UI is the agent's interface — single source of truth. Users watch, learn, and take over. No separate tools to build.
npm install polter
The AI assistant on the right sends a single sentence. Polter drives every click on the left.
Generative UI generates new interfaces on the fly. Agent-Driven UI drives the one you already built.
You build your UI. Then you build a whole separate set of agent tools — API endpoints, handlers, schemas — all duplicating what the UI already does.
The agent works behind the scenes or generates throwaway UI. Either way, users never learn your actual interface. Permanent dependency.
Single source of truth. The agent drives your real buttons, dropdowns, and forms — users watch and learn. After twice, they do it themselves. Zero extra tools to build.
Guided mode or instant. One prop.
Wrap any element. Polter handles the rest.
Schemas auto-generate. Send to any LLM.
Scroll, dim, spotlight, cursor, click. The user sees everything.
Open dropdown, select option. Sequential steps with visual guidance.
Mounted = exists. Unmounted = gone. Agent can't hallucinate clicks on things that aren't there.
Ghost cursor glides to each target before clicking. Opt-out with one prop.
Types character-by-character into real inputs. Triggers React events properly.
Guided for learning. Instant for power users. Switch anytime.
React + Zod peer deps only. No runtime dependencies.
Portals, popovers, virtualized lists. Opens the container, then finds the target.
Test actions, inspect schemas, debug execution. No setup.