You authorize it. The agent runs with it.

Hand your agent the whole web —
you decide what it may touch.

Twin Browser gives your AI agent a real browser it can drive anywhere: reach any site, pull any data, sign into any account you connect. You set the guardrails and approve what matters — it takes the lead on everything else, so the work just gets done.

  • OpenAI
  • Anthropic
  • LangChain
  • AutoGen
  • Claude
  • Cursor
  • Playwright
  • MCP
  • CrewAI
  • Llama

The platform

Real work in a real browser — on your terms.

It pauses for you, then picks up where it left off

When a step needs a person — an approval you must give, an MFA prompt on an authorized flow — the run pauses at the gate instead of failing. You approve, and execution resumes from exactly where it stopped. No restart, no lost state — you decide what it may touch as it goes.

How handoff works
approval · MFAPaused → approved → resumed
How delegation works

Hand off the goal. Keep the controls.

You give a plain-language goal and the accounts it may use; the agent does the real work in a live browser while you approve what matters. Repeated flows compile into skills and replay near-free, so the bill falls with usage instead of climbing.

01

Compile once

The DOM → indexed-state compiler turns a live page into a compact numbered map of what an agent can act on. The planner discovers the goal once and minimizes it to the shortest reliable route — a skill.

[1] Button "Log in"
discover → 7 steps
minimize → 2 steps
02

Semantic cache

A re-phrased request is vector-matched to a skill you already compiled for that host and adapted to the new values — a cache hit, roughly 5× cheaper than a cold compile, instead of starting over.

dispatch → vector match
adapt    → new values
cost     → ~0.2×
03

Deterministic replay

Compiled skills are descriptor-based and survive DOM rotation. Replay runs the minimal route by name with no model in the loop — the same flow, every time, with zero LLM calls.

run_skill → by name
llm calls → 0
result    → deterministic
04

Marginal cost ≈ 0

The more your agents repeat a task, the more runs hit replay — so cost per run trends toward zero. A cross-tenant skill corpus compounds it: a skill compiled once can be safely reused.

runs ↑
cost/run ↓
→ trends to $0
The honest comparison

Reach of an agent, control of a co-pilot.

LLM-per-run browser infra reaches anywhere but runs unsupervised and bills up; generic RPA is cheap to license but brittle and blind to change. Twin hands your agent the whole web while you keep the guardrails — and the cost curve bends down.

Re-run-the-LLM browser infraGeneric RPATwin Browser
Drives any site from a plain goal
Yes: Yes — but re-reasons from scratch each time
No: No — brittle recorded selectors only
Yes: Plain-language goal on any site you authorize
You stay in control mid-run
No: Fire-and-forget; little to approve or pause
No: Unattended scripts, no live gate
Yes: Pause, approve, resume — plus per-host policy + audit log
Signs into accounts you connect
Depends on your own plumbing
No: Hard-coded creds, no vault
Yes: Encrypted vault; the run URL is your authorization
Survives DOM rotation
Yes: Yes, by re-paying the model every run
No: No — selectors rot, scripts shatter
Yes: Descriptor-based skills replay deterministically
Distribution
Yes: Usually an SDK
No: Desktop studio, heavy setup
Yes: REST + MCP + hosted dashboard
Cost as usage grows
No: Climbs — billed per browser-hour, step, or token
No: Flat licence, but breaks need paid rework
Yes: Falls — cache hits and replays trend to $0

Fair caveat: re-running the LLM is the simplest thing to ship, and fine at low volume. Twin's edge shows up when the same flow runs again and again — which is exactly when an RPA-replacement product needs cost-per-1k-runs to fall, not rise.

Two ways to run it

Operators click. Builders call. Same engine.

Whether you never write a line of code or live in your IDE, you hand the agent a goal and keep the controls — every run authenticated, isolated, logged, and yours to pause or approve.

No code

The hosted dashboard

Describe a goal, give it a target URL, and watch it run in a real-time live view. Compile skills, replay them, store credentials in the vault, and review session video — no SDK, no agent to wire up.

  • Real-time live view + session video
  • Agent & skill library, one-click replay
  • Credential vault, usage-based credits
Start in the dashboard

Builders

The API + MCP

The same engine behind a small versioned REST API and an MCP server your agent drives natively. Bearer-key auth, per-tenant isolation, an audit log — drop it into Cursor, Claude, LangChain, or AutoGen in one line.

  • REST under /api/v1/* with Bearer keys
  • MCP tools: run · compile_skill · run_skill
  • LangChain & AutoGen tool adapters
Read the API reference
Authorized automation

Automates the web where you're authorized.

Twin is built for first-party sites, operator-approved automation, internal RPA, accessibility, and authorized testing. Auth, billing, and audit logging run on every call. It is not a CAPTCHA-bypass-for-hire or anti-bot evasion service.

Default-deny RLS

Tenancy is enforced in Postgres, not just the app. Every row is isolated by tenant with row-level security on by default.

Run URL = authorization

Each call is authenticated with your key and acts on exactly the target URL you provide — you hold the authorization, and it is stamped into the record.

Credential vault

Secrets are encrypted at rest, filled only at run time, and redacted from every log. Per-tenant keys, never shared.

Full audit log

Every run records its goal, path, success condition, and the target it acted on — a complete trail of what each agent did and where.

Pricing

Pay for the work your agent does.

You pay for what your agent does, not per seat or per browser-hour. A read costs a credit; a solved semantic flow costs more — then every replay drops back to one. Discovery is the only premium you pay, so cost falls as you scale.

$29/mo entry plan · free to start
  • Pay for actions, not seats
  • Free to start — no credit card
  • Compiled-skill replays cost a single credit
  • LLM cost metered and passed through at 1×
  • Pay-as-you-go auto top-up — no surprise stops

Transparent rate card at /api/v1/pricing.

FAQ

Questions, answered.

What is Twin Browser?
Twin Browser is the browser layer for AI agents. Hand your agent a plain-language goal and it does the real work in a live browser — reaching any site, pulling any data, and signing into the accounts you connect — while you set the guardrails and approve what matters. Under the hood it turns a goal into deterministic, replayable action, so repeated flows get near-free.
Why does cost fall the more my agents run?
Most browser infra re-runs the LLM on every execution, so cost climbs with usage. Twin pays the model once at cold compile, serves re-phrased requests from the semantic cache (~5× cheaper), and replays compiled skills with no model in the loop — so marginal cost per run trends toward zero.
How do I call it?
Through a versioned REST API under /api/v1/* with Bearer-key auth, an MCP server (tools: run, compile_skill, run_skill) for Cursor, Claude Desktop, Claude Code, and Cline, or one-line LangChain and AutoGen tool adapters. There is also a no-code hosted dashboard.
What does it cost?
Usage-based credits, with an entry plan from $29/mo and a free tier to start. LLM cost is metered per call and passed through at 1×, with a transparent rate card at /api/v1/pricing. Pay-as-you-go auto top-up keeps runs from stopping unexpectedly.
Is it a CAPTCHA-bypass or anti-bot evasion service?
No. Twin automates the web where you are authorized — first-party sites, operator-approved automation, internal RPA, accessibility, and authorized testing. The run’s target URL is the authorization signal, and auth, billing, and audit logging run on every call. The backend uses default-deny RLS, per-tenant API keys, an audit log, and a credential vault.
What is the cross-tenant skill corpus?
Sanitized skill skeletons are safely reused across tenants, so your cache-hit rate climbs as more teams automate the same hosts. Your values, credentials, and exact paths never cross tenants.

Put your agent to work — you stay in control.

Free to start. Connect an account, set your guardrails, and hand off the busywork — your agent runs it live in a real browser, from MCP, REST, or the hosted dashboard.

Any site · Any login you authorize · Guardrails you control