Local-first co-browse runtime · open source
Browgent is not another chat sidebar. It is a desktop runtime where an agent acts on your actual tabs and session — and you are always one click from taking the wheel. Attach Claude Code (MCP) or Playwright (CDP) to the same tabs, behind a policy engine with exportable trajectories.
or watch the 60-second flow ↓ · Star on GitHub · Builders guide · Become a design partner
Proof you can run today: clone it, npm run dev, attach Claude Code over MCP,
and take over a login mid-task — no signup, no cloud, no waitlist. MIT-licensed, local-first, model-agnostic.
This is an early runtime, honest about its stage: the wedge below is the pitch, not a user chart.
ask_humancheckout?Looping illustration of the co-browse + takeover flow — not a screen recording. A real demo drops in above.
Same tab tree. Ownership badges. Takeover → resume without losing the session.
STDIO MCP for Claude Code / Cursor. Playwright over CDP on the same cookies.
Confirm sensitive actions, host gates, modes, exportable trajectory JSON for evals.
BrowserOS is a browser for end-users to automate their own browsing; Browgent is a runtime you attach agents and Playwright to, with a human in the loop. Comet, Dia, and Atlas are the consumer-category reference — polished AI browsers with a closed assistant.
| Product | Job |
|---|---|
| Browgent | Local co-browse runtime you attach agents + Playwright to (HITL) |
| BrowserOS | Open-source agentic browser for end-users (ties us on OSS + local) |
| Comet / Dia / Atlas | Closed consumer AI browsers with a built-in assistant |
| Browserbase / Steel | Cloud multi-tenant headless fleets |
| Playwright MCP alone | Dev tools without a shared human UI or policy chrome |
npm run devmcp · :17342 (token in userData)npm run mcp → wire Claude CodeBeachhead: developers building browser agents that keep failing on real login / SSO / CAPTCHA walls. Browgent gives those agents a local, logged-in session and a human who can step in and hand control back — with policy and an audit trail.
Also useful for HITL automation/ops teams and eval/safety labs that need exportable trajectories.
Building browser agents that die on login walls? We're onboarding a small set of partners for free support in exchange for honest feedback (and an optional quote).