Add to Chrome
rtrvr.ai is an AI-powered web automation platform that can retrieve data, fill forms, navigate complex sites, and integrate with APIs — all without you writing a single line of code. It works as a DOM-native agent: instead of taking screenshots, it reads and acts on the page's actual structure, giving it human-like precision with machine-like speed.
Three Ways to Use rtrvr.ai
Every capability in rtrvr.ai — recordings, tools, knowledge bases, schedules, triggers — works across multiple surfaces. Pick the one that fits your workflow, or combine them.
| Platform | Best For | Get Started |
|---|---|---|
| Chrome Extension | Interactive browsing, authenticated sites, building & testing workflows | Install from Chrome Web Store → Open side panel (Ctrl/⌃+R) |
| Cloud | 24/7 headless execution, high-volume batches, always-on monitoring | Export workflows from the extension → rtrvr.ai/cloud |
| HTTP API & MCP | Backend integration, CI/CD, Claude.ai, programmatic control | POST to mcp.rtrvr.ai or the /agent endpoint → see API docs |
Quick Start — Chrome Extension
- 01
Open the side panel: Windows Ctrl+R / Mac ⌃+R
- 02
Type a natural-language request, or use shortcuts: @ for tools, # for tabs, / for saved shortcuts
- 03
Watch the AI execute in real-time across one or many tabs — give feedback if needed
- 04
When a task works, save it as a Shortcut, Schedule, or Trigger for instant reuse
Quick Start — API
curl -X POST "https://api.rtrvr.ai/agent" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": "Go to example.com and extract the main heading",
"urls": ["https://example.com"]
}'How the Agent Works
rtrvr.ai isn't a single AI model — it's a sophisticated orchestration system. A Planning Agent receives your request, breaks it into steps, and delegates to 20+ specialized sub-agents. Each sub-agent is an expert at a specific capability.
| Sub-Agent | Responsibility |
|---|---|
| Action Agent | Clicks, typing, navigation, form interactions |
| Extraction Agent | Structured data extraction from the DOM |
| Crawl Agent | Pagination, multi-page discovery, link following |
| PDF / File Agent | Read PDFs, fill forms, create documents, handle uploads |
| Sheet Agent | Read from / write to Google Sheets in parallel |
| Tool Agent | Call MCP servers, custom JavaScript functions, external APIs |
Models & Bring Your Own Key
Managed runs use GLM 5.3 Flash on the free plan (in ad-supported Free Mode, with a daily fair-use limit), with DeepSeek Flash, DeepSeek Pro and Gemini Flash also selectable on paid plans. Gemini Pro has been retired as a managed option — saved tasks that still request it run on Gemini Flash automatically. Pick your model from Model Settings in the composer.
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 — and 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.
Files & PDFs
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").
Files the agent downloads go through Chrome's normal download flow, so in the extension they land in your browser's Downloads folder — open chrome://downloads to find them (the run's result lists each one). In cloud runs they're backed up to your Files. If a task saves several files and some are missing, Chrome probably blocked the extra automatic downloads — click the blocked-downloads icon in the address bar, choose "Always allow", and re-run. Details in Web agent → Files & PDFs.
Context Tips
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
Getting Help
Stuck on a website or need guidance? Reach out via support@rtrvr.ai or join the active Discord community at rtrvr.ai/discord.