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 worksHand 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.
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 stepsSemantic 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×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 → deterministicMarginal 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 $0Reach 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 infra | Generic RPA | Twin 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.
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
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
Delegate the busywork. Keep control.
Twin drives the web where you're authorized — first-party sites, operator-approved automation, internal RPA, accessibility, and authorized testing — with you setting the guardrails on every run.
AI agents at volume
Hand your agent the whole web from MCP or REST — it reaches any site, pulls any data, and signs into the accounts you connect. Repeat flows replay near-free.
ExploreRPA replacement
Swap brittle recorded bots for descriptor-based skills that survive DOM rotation and do the real work — with a live gate to pause, approve, and resume.
ExploreInternal & authorized testing
Automate first-party apps, operator-approved flows, and end-to-end checks — every run authenticated, scoped, and logged.
ExploreAccessibility & data ops
Token-efficient page state and human-in-the-loop handoff make repetitive, authorized web work reliable and auditable.
ExploreAutomates 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.
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.
- 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.
Questions, answered.
What is Twin Browser?
Why does cost fall the more my agents run?
How do I call it?
What does it cost?
Is it a CAPTCHA-bypass or anti-bot evasion service?
What is the cross-tenant skill corpus?
Everything in one place
Dig into how Twin works, how to build on it, and where teams run it.
Product
Hand your agent the web, keep the guardrails — everything it ships with.
Learn moreAPI
The versioned REST API under /api/v1/* — Bearer keys, OpenAPI.
Learn moreMCP
Drive Twin from Cursor, Claude, and Cline with run / compile_skill / run_skill.
Learn moreDocs
Quickstarts, references, and how the execution model fits together.
Learn moreUse cases
AI agents, RPA replacement, internal automation, and authorized testing.
Learn moreCompare
Twin vs re-run-the-LLM browser infra and generic RPA.
Learn moreGuides
Step-by-step walkthroughs for compiling and replaying skills.
Learn moreGlossary
Semantic cache, indexed DOM state, skill corpus — defined.
Learn morePut 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