Web Agent

Free Mode includes supported AI models and Cloud browser time for tasks you start in the extension or Cloud dashboard. No AI API key or paid AI subscription is required. Sponsored cards and a daily fair-use allowance apply. Your account shows the current allowance and reset time. When you reach it, wait for the reset, use your own AI provider, or choose a paid plan. Your provider may charge for its usage.

New accounts receive 100 one-time welcome credits for paid usage. They are separate from the recurring Free Mode allowance. One schedule that runs once a day or less often, in the Cloud or in your Chrome, is included, paid from the daily allowance. More schedules, faster schedules, triggers, cookie sync, API runs, rtrvr's agent over MCP, and WhatsApp tasks require a paid plan. Browser tools that let your own AI drive your Chrome over MCP are free on every plan. Data enrichment and managed proxies can use credits separately.

On the free plan, Cloud API calls made with an API key, the MCP Cloud tools (cloud_agent, cloud_scrape, and agent or scrape when they run in Cloud), and WhatsApp tasks need a paid plan, as does running rtrvr's agent in your Chrome through API or MCP. Free Mode covers the tasks you start in the extension or Cloud dashboard. On a paid plan, API, MCP, and WhatsApp runs use credits for the resources they consume. Free Mode involves sponsored content in both the Chrome extension and Cloud, as described in the Terms and Privacy Notice. Compare plans, read the Free Mode terms, or see the Privacy Notice.

You can start a task on rtrvr.ai/cloud and run it in the Chrome browser on your computer. Open Routing below the prompt and choose your online browser under From your computer. Once selected, the button shows your browser's name, such as Chrome on MacIntel. Starting a Chrome task from the website is separate from paid API/MCP access. Eligible interactive tasks can use Free Mode.

• 01

  Install the rtrvr extension, then sign in to the extension and website with the same rtrvr account.

• 02

  Keep that Chrome profile open and signed in to the site you want to use.

• 03

  Select the browser in Routing, write your task, and send it. The website shows the progress and result.

• 04

  To run in Cloud instead, open the same menu and choose an option under From the cloud. Choose the accounts the task can use in Secure logins.

Search Instagram by topic, find a creator, and ask rtrvr to follow, like, or comment. This walkthrough runs from the website through a Chrome profile already signed in to Instagram.

IN THIS WALKTHROUGHPlay videoFind creators. Engage with their posts.

Find Instagram creators and engage with their posts

Play Find Instagram creators and engage with their posts

Choose the Chrome profile signed in to the Instagram account you want to use. Tell rtrvr which actions to take, then check the profile and post links in the result. To save a creator list to Google Sheets, connect Google Drive.

When you issue a command, the Planner agent orchestrates 20+ specialized sub-agents to complete the task:

• 01

  Action Agent: Handles clicks, typing, and navigation

• 02

  Extraction Agent: Identifies and structures data from the DOM

• 03

  Crawl Agent: Manages pagination and multi-page discovery

• 04

  PDF / File Agent: Reads and fills complex forms, uploads documents

The agent can reference multiple open tabs simultaneously: comparing data across sites, moving information between systems, or processing dozens of URLs in parallel via Sheets Workflows.

Once a multi-step workflow succeeds, you can replay its recorded steps without another planning pass. Shortcuts, Schedules, and Triggers can build on that recording; results still depend on the page and inputs available at run time.

Free Mode includes the supported models shown in Model Settings. You do not need your own AI subscription or API key to start. Paid plans unlock additional managed models and features; your account shows the current choices.

Save credits by bringing your own key: the "Add your LLM API" flow accepts keys from any major provider: OpenAI GPT models, Google Gemini, Meta Model API (Muse Spark), DeepSeek, OpenRouter models (MiniMax, Hunyuan, and more), or your own local/custom endpoint. You can also sign in with your ChatGPT plan directly. Keys are stored encrypted and work in cloud runs too. For Gemini specifically, typing /add-gemini-key in the extension walks you through getting a free key from Google AI Studio. If your own provider errors mid-task, the run falls back to a platform model so it completes: covered by Free Mode on the free plan while today's allowance lasts, billed in credits otherwise. Your key runs the model, so nothing deducts from the free plan's daily Free Mode allowance.

To try Jev alongside your selected model, turn on Try Jev in the same model picker. This experimental option lets Jev choose browser actions while your model continues to plan and write. It is off by default and paused in Private Mode. See the Jev setup guide for screenshots, a walkthrough, and what to expect.

Every task carries a credit ceiling: a cap on what one run may spend before it stops to check with you. It exists because a task that loops, crawls further than expected, or gets stuck retrying can otherwise burn through credits unattended. The default is 100 credits on paid plans and 25 on the Free plan; the typical task finishes in well under 15.

When a run reaches the ceiling it pauses and shows what it has spent, what it produced so far, and what is still outstanding. Answer "Continue" and it resumes from exactly where it stopped with a fresh budget (nothing already done is repeated), or "Stop here" to keep the result and end the task. Scheduled runs are the exception: nobody is watching a cron run, so they stop at the ceiling and report their partial work instead of waiting forever for an answer.

Raising or turning off the ceiling

The ceiling is yours to set. If your work genuinely costs 200-400 credits a run, raise it once and the agent stops interrupting you:

• 01

  Extension: Settings (the gear at the bottom of the side panel) → Agent Settings → "Credit Ceiling / Task".

• 02

  Cloud: Settings → Storage & Execution → Credit Ceiling / Task.

• 03

  API: maxCredits on a single /agent call (shorthand for options.limits.creditCeiling.credits), which overrides the saved setting for that run. See Agent API.

• 04

  MCP: max_credits on an agent, planner or cloud_agent call, the same budget for that one run. See MCP.

Setting the value to 0 turns the check off entirely. Blank (cloud) or the extension's disabled state falls back to the plan default. Each surface keeps its own value: the extension's setting governs extension runs, the cloud setting governs cloud and API runs.

Drag and drop files into the chat or attach them via the toolbar. The agent has specialized capabilities for PDFs: reading content, filling form fields, and generating new documents. It can also upload attached files to web pages when prompted (e.g., "fill this job application and upload my resume").

File size limits

• 01

  Signed in, you can attach files up to 128 MB each: in the extension side panel, the cloud composer, the Agent API (files) and MCP file parameters. In the extension's Private Mode the limit is 20 MB.

• 02

  The model reads files up to 20 MB. For a larger file it sees only the name, type and size, and the agent can still upload that file into a web page or pass it on to tools and later steps.

• 03

  The agent can also upload a file into a page straight from a link (for example a signed download URL). Files up to 1 GB work this way, and the file is downloaded once.

Where downloaded files go

When the agent saves a file (a PDF it opened, or a document it generated and you asked it to download), it uses Chrome's normal download flow, so the file lands in your browser's Downloads folder. The run's result lists each file (Downloaded: name.pdf) and shows a 💾 chip; click it, or open chrome://downloads in a new tab, to see every file with a "Show in folder" link.

• 01

  Extension runs: files are on your computer, in Chrome's Downloads folder, and chrome://downloads is the quickest way to find them.

• 02

  Cloud runs: the browser isn't yours, so downloaded files are backed up to your Files and attached to the run as file artifacts you can open or download.

• 03

  Generated PDFs and webpages are stored for you and linked from the result (PDF: / Webpage:); say "and download it" to also save a local copy.

Everything in your chat (messages, files, images) becomes context for the AI. Keeping context clean leads to better results.

• 01

  Start fresh chats for new tasks: stale context can confuse the planner

• 02

  Only enable the MCP/custom tools you actually need for the current task

• 03

  Use Personal Context in settings to store persistent info (resume, company details) the agent remembers across all chats

• 04

  Click the ✨ Enhance button (Cmd/Ctrl+P) to have a specialized model rewrite your prompt for clarity before sending

The Chrome Extension is where you build and test workflows. Export successful workflows to rtrvr.ai Cloud for 24/7 headless execution, no laptop required. Recordings, tools, and KB context travel with the workflow automatically.

• 01

  Export any workflow from the extension to Cloud with one click

• 02

  Scale to thousands of parallel URLs via the API

• 03

  Connect your account to WhatsApp: send text or voice messages to trigger automations and receive results on your phone

• 04

  Share your best automations via link: recipients import with one click, including recordings, tools, and all context