A browser built for your AI agent

Because browser automation is bursty. Most people do not use an agent browser every day, and a subscription punishes that. You buy a pack and paid credits never expire. No renewal anxiety, no cancel-flow dark patterns.

Nothing breaks. The next tool call returns a polite message with a top-up link instead of running, and Claude relays it to you. Your installation, saved flows, and login states are untouched; buy a pack and the same call works again seconds later. We email you once when you hit zero, and that's it.

Reflex works with any client that can run local MCP servers: Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, and others. ChatGPT currently supports remote connectors rather than local MCP servers, so not yet; the moment that changes, Reflex will work there too, since it speaks standard MCP.

It is, and Microsoft maintains it with support for Firefox/WebKit and network mocking. Reflex offers batched actions, scoped reads, isolated sessions, and detailed failure reports. Historical June 2026 tool runs used 14 Playwright MCP calls and ~56K estimated response tokens versus 6 calls and ~13K for Reflex across three mutually verified flows. Overall completion was 3 of 6 versus 5 of 6; some failures came from the benchmark runner. Tokens were estimated from characters, and current Playwright MCP can return file links and batch forms or scripts. In the October 2026 model-driven comparison, the unreleased Reflex build averaged 20% less time, 21% fewer total model tokens (including cached input), and 56% fewer MCP requests versus Playwright MCP across three tasks. All 27 runs succeeded. See /benchmarks for task-level results and separate historical highlights.

Reflex drives your installed Chrome with its own profile. Log in to a site once in that window and tell Reflex to save the session; it stores cookies and localStorage locally on your disk and reuses them on demand. Your logins persist across tasks and never leave your machine.

One credit per tool call. A task using one open call and one batched action costs 2 credits; extra reads, pages, and retries add calls. The historical June 2026 tool benchmark used 14 Playwright MCP calls versus 6 Reflex calls across three mutually verified flows. Current tools and the agent's workflow can change that comparison. Failed calls also cost one credit and return a failure report with details to help you retry.

Only for the metering layer, and it never blocks your work. The key is validated when the server starts, credits are decremented against a local cached balance, and usage syncs in the background with an offline buffer. Browsing localhost or an intranet app works fine.

Paid credits never expire. The 30 free signup credits expire after 14 days; they exist so you can evaluate Reflex properly, not as a permanent free tier.

If you bought a pack and it isn't working out, email support within 14 days and we refund the unused balance, no interrogation. Refunds for consumed credits are case by case, biased toward yes; arguing over $9 is not a business we want to be in.