Pricing

Free

Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.

Prices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.

Use Cases

Teams use OpenBrowserHarness to navigate, scroll, fill forms, and extract content from real web pages under human approval.
Users use the side panel to chat with an agent that plans, calls tools, tracks todos, and reports back.
Developers use humanized browser control with Bezier-curve mouse moves, per-keystroke typing, inertial scrolling, and landing-point jitter.
Users watch every action through a visible virtual cursor with a neon comet cursor, motion trail, click shockwaves, and keystroke/scroll pulses.
Teams use deep page reading with snapshots that pierce Shadow DOM and iframes, a screenshot tool for multimodal models, and in-page evaluation for verification.
Users bring their own model from DeepSeek, 智谱 BigModel / GLM Coding Plan, or any OpenAI-compatible, Anthropic-protocol, or local Ollama endpoint.
Teams control agent actions with three permission tiers, per-action approval cards, and session logs exportable for audit.
Developers use inherited dsh features such as skills, plan mode, goals/todos, subagents, and session persistence.

Chrome and Edge sidebar agent

Plans tasks and tracks todos

Navigates pages and fills forms

Extracts content across frames and Shadow DOM

Humanized mouse typing and scrolling

Visible cursor shows browser actions

Supports multiple model endpoint protocols

Action approvals and exportable session logs

No reviews yet. Be the first to share your experience!