I open-sourced DomA: an AI automation agent for the browser

Description and use

DomA is a Chrome/Edge extension that runs an AI agent from a side panel, preserving user sessions and extensions. It uses screenshot overlays, an inner Jev loop to reduce LLM calls, and reusable skills to improve accuracy on real sites.

Problem

Browser automation agents often fail on real sites due to fragile selectors, slow LLM round‑trips, and lack of reusable procedures.

Outcome

DomA reduces LLM round‑trips, improves accuracy on real sites, and enables reusable automation skills while preserving user session data.

Workflow

• 1. User opens DomA side panel in Chrome/Edge
• 2. Agent captures a screenshot with numbered overlays (Set‑of‑Mark grounding)
• 3. Agent selects index‑based actions (click, type, navigate)
• 4. Optional Jev inner loop executes multiple grounded steps locally
• 5. Agent verifies progress and continues until goal achieved or hands back to main LLM
• 6. Successful procedures are saved as Agent Skills for future reuse

Evidence

DomA is a Chrome/Edge extension, not a standalone AI browser and not a hosted “cloud browser.”

Source

The real pain isn’t “can it click?” — it’s accuracy

Source

Jev is DomA’s optional inner loop on browser_screenshot (act/verify)

Source