Products
AI Benchmark
Desktop
Mobile
Monthly visits
34.3K
Up36.6%MoMSep 2026
Public revenue
Undisclosed
No public revenue evidence yet
Entry price
$9.99/mo
Lower than 87% of peersNiche median $26/mo
Creators
Arjun Chintapalli
No social account linkedCo-created with Bhavani Kalisetty
Launched
23mo ago
2024-12-23 · Est.

Traffic

Monthly visitsData through Sep 2026 · Oct 2026 pending
Events12 changes · 11 marketing moves

Marketing moves

Launches, search & content, referrals, promotions
  • Launched on Product HuntLaunch

    Free AI browser agent: find leads, reach out, apply to jobs

    Oct 14 · 31d agoLaunch page

    At the time: 34.3K visits/mo12 concurrent moves
  • Launched on Show HN (9 pts)Launch

    DeepSeek Flash inverted the economics of agent products — There is an adversarial relationship between developers and big model labs. Model labs charged developers higher API prices to subsidize t…

    Jun 25 · 5mo agoLaunch page

  • Launched on Show HN (2 pts)Launch

    AI agents should browse your site, not call your API — We compared four architectures for putting AI agents on websites — RAG bots, API-tool agents(WebMCP), code-writing sandboxes (Cloudflare A…

    Apr 17 · 7mo agoLaunch page

  • Launched on Show HN (46 pts · 17 comments)Launch

    AI Subroutines – Run automation scripts inside your browser tab — We built AI Subroutines in rtrvr.ai. Record a browser task once, save it as a callable tool, replay it at: zero token cost, zero LLM infer…

    Apr 17 · 7mo agoLaunch page

  • Launched on Show HN (5 pts)Launch

    MCP is for tools. A2A is for agents. What's for websites? — HTTP lets agents fetch pages. Cloudflare's Markdown for Agents lets them fetch more efficiently. MCP (Anthropic) connects agents to develo…

    Apr 12 · 7mo agoLaunch page

Third-party reviews & case dossiers

Acquisition breakdowns, engineer reviews & open-source metrics
Show HN
2024-12-23Source
Post excerpt:
Hey HN, I'm excited to share rtrvr.ai, a Chrome extension that brings the power of AI agents to your everyday web browsing. It's designed to automate complex web tasks, extract structured data from any website, and integrate with your favorite tools as you browse using AI Function Calling [ie: “Send this page summary as Slack message”]. The core idea is to l
Show HN
2025-02-21Source
Post excerpt:
We initially launched rtrvr.ai: an AI Web Agent Chrome Extension that can autonomously complete tasks, scrape data to Sheets and call API's as you browse Chrome with just prompts! We showcased out AI Agent: - Researching and Trading Stocks: https://www.youtube.com/watch?v=1glo1GuojeM - Automating LinkedIn Outbound: https://www.youtube.com/watch?v=Ct__f-fLS8A
Show HN
2025-06-22Source
Post excerpt:
We just benchmarked our agent, rtrvr.ai, on the Halluminate (YC S25) Web Bench, and rtrvr.ai achieved a new State-of-the-Art performance with an 81% success rate. For perspective, this surpasses not only all other autonomous agents but also the human-intervention baseline of OpenAI's Operator (76.5%). It also completes tasks an astonishing 7x faster than the
Show HN
2025-11-12Source
Post excerpt:
Hey HN, I'm Arjun, one of the founders of rtrvr.ai. For the past year, we've been building and iterating on an in-browser AI agent. But a few months ago, we hit a wall in our approach and decided to tear everything down and rebuild from first principles. The result is what we're re-launching today. The Problem/Insight: We kept coming back to a simple, naggin
Show HN
2026-01-05Source
Post excerpt:
Hi HN, Bhavani here (rtrvr.ai). We build DOM-native web agents (no screenshot-based vision, no CDP/Playwright debugger-port control). We handle captchas natively including Google reCAPTCHA image challenges by traversing cross-origin iframes and shadow DOM. The latency is high on this one currently. The problem: when debugging image selection captchas ("selec
Show HN
2026-02-13Source
Post excerpt:
Rover is the world's first Embeddable Web Agent, a chat widget that lives on your website and takes real actions for your users. Clicks buttons. Fills forms. Runs checkout. Guides onboarding. All inside your UI. One script tag. No APIs to expose. No code to maintain. We built Rover because we think websites need their own conversational agentic interfaces as
Show HN
2026-04-12Source
Post excerpt:
HTTP lets agents fetch pages. Cloudflare's Markdown for Agents lets them fetch more efficiently. MCP (Anthropic) connects agents to developer-defined tools. A2A (Google) lets agents delegate to other agents. But there's a missing layer: how does an agent execute a multi-step task on a website -- add to cart, fill a form, complete a checkout - with the site o
Show HN
2026-04-17Source
Post excerpt:
We built AI Subroutines in rtrvr.ai. Record a browser task once, save it as a callable tool, replay it at: zero token cost, zero LLM inference delay, and zero mistakes. The subroutine itself is a deterministic script composed of discovered network calls hitting the site's backend as well as page interactions like click/type/find. The key architectural decisi
Show HN
2026-04-17Source
Post excerpt:
We compared four architectures for putting AI agents on websites — RAG bots, API-tool agents(WebMCP), code-writing sandboxes (Cloudflare Agent Lee), and DOM-native execution. Three of them force you to maintain a parallel engineering surface. The DOM already has live state, user auth, and permissions baked in. A structural breakdown of why.
Show HN
2026-06-25Source
Post excerpt:
There is an adversarial relationship between developers and big model labs. Model labs charged developers higher API prices to subsidize their own agent harness offerings. Think Anthropic charging 5x higher Claude API prices to subsidize consumer subscriptions. So Cursor in a way was subsidizing their own direct competitor. DeepSeek V4 Flash totally inverted

Open Source & Agent Ecosystem

GitHub · MCP / Skill
Last commit 2026-05-24
GitHub Stars
★ 22
Forks
6
License
See repository
Primary language
—

Store data

Chrome Web Store
Chrome Web Store Chrome Web Store
Update date not synced
Rating
Rating not syncedRating count not synced
New ratings last mo
—
Price & IAP
FreeIAP data not synced
Current version
—Store metadata

Store assets, rating histograms, install tiers, and screenshots are synced from Apple App Store, Google Play, and Chrome Web Store.

Traffic sources

Sep 2026

Traffic breakdown

Channels

  • Direct54%
  • Organic Search29%
  • Social11%
  • Other6%

Countries

  • United States42%
  • India19%
  • Canada8%
  • South Korea4%
  • France4%

Search

Domain authority —Domain registered 2023-11-09

KeywordMonthly volume
retriever ai1,470
rtrvr ai930
retreaver affiliate group community240
retriver ai240
rtrvr90

Traffic data: Vaneform

Pricing

Free
$0
One schedule that runs once a day or less often
Starter
$9.99/mo
Billed annually $8.33/mo-17%
1,000 credits each month
Pro
$29.99/mo
Billed annually $25/mo-17%
3,000 credits each month · Workspaces: 1 seat included, add more for $9.99/seat
Team
$99.99/mo
Billed annually $83.33/mo-17%
10,000 credits each month · Workspaces: 3 seats included, add more for $9.99/seat
Scale
$499.99/mo
Billed annually $416.67/mo-17%
50,000 credits each month · Workspaces: 10 seats included, add more for $9.99/seat

Trial: None · 4 paid tiers ($9.99–$499.99) · Up to 17% off annually · Observed 2026-11-04 · Pricing page

Entry price $9.99/mo, Lower than 87% of peers; “Agent Builders & Platforms” median is $26/mo.View pricing benchmark

Pages & changes

Tracked since 2026-07-31

Key pages

Weekly snapshots

Changes

  1. Nov 1 · 13d ago

    Homepage headline (H1) changed to “Your free AI browser agent.”Positioning

    Retrieve the Web with AI→Your free AI browser agent.

  2. Nov 1 · 13d ago

    Adopted technology: CloudflareFeatures

    —→Cloudflare

  3. Nov 1 · 13d ago

    Adopted technology: Cloudflare Bot ManagementFeatures

    —→Cloudflare Bot Management

  4. Nov 1 · 13d ago

    Removed technology: Google Font APIFeatures

    Google Font API→—

  5. Nov 1 · 13d ago

    Removed technology: Google WorkspaceFeatures

    Google Workspace→—

  6. Nov 1 · 13d ago

    Adopted technology: RSSFeatures

    —→RSS

Design

First-screen visual analysis & :root CSS

Soft & Friendly (Light canvas, balanced density) featuring split copy & visual layout and illustration / character art visuals.

First-screen preview · click to zoom

First-screen pitch & conversion flow

“Your free AI browser agent.”

Split Copy & Visual hero structure paired with download app / install extension CTA and user count, rating, or key metrics.

Conversion path: Split Copy & Visual + Illustration / Character Art → Download App / Install Extension · Trust bar: User Count, Rating, or Key Metrics

Palette · click to copy

5-D design score7.9 / 10
Typography
8.0
Color & Contrast
8.0
Layout & Spacing
8.0
Craft & Polish
8.0
Distinctiveness
7.0

Structure

Fonts
Inter
Primary visual
Illustration / Character Art
Social proof
User Count, Rating, or Key Metrics
Navigation
Full-Width Top Bar
Theme & density
Light · Balanced
Corners & depth
Small Radius · Hairline borders
Preview full AI design brief (includes :root CSS variables & layout rules)Style tokens only; never copy brand names, logos, copy, or images
# Design Brief: Soft & Friendly (with Editorial)

Warm low-saturation pastels, generous rounded corners, and approachable illustrations.

## Design Tokens

```css
:root {
  --background: #f6f3ea;
  --surface: #ffffff;
  --foreground: #111111;
  --muted-foreground: #6b6b6b;
  --accent: #e4572e;
  --radius: 4px;
  --font-heading: "Inter", ui-sans-serif, system-ui, sans-serif;
  --font-body: "Inter", ui-sans-serif, system-ui, sans-serif;
}
```

Color area ratio: Background #F6F3EA (~46%) · Surface #FFFFFF (~12%) · Text #111111 (~16%) · Muted Text #6B6B6B (~8%) · Accent #E4572E (~18%). Background and surface dominate the canvas; reserve the accent color for primary buttons and active states.

## Layout & Conversion Structure

- Hero layout: Split Copy & Visual
- Navigation: Full-Width Top Bar
- Theme & density: Light · Balanced
- Border radius & elevation: Small Radius; no drop shadows—separate layers with hairline borders and whitespace
- Primary visual medium: Illustration / Character Art
- Conversion CTA: Download App / Install Extension · Trust bar uses User Count, Rating, or Key Metrics
- Headline hook: Category Positioning Anchor
- Hero components: Custom Illustration, Metrics Strip, Floating Multi-Cards
- Spatial layout notes: Split Copy & Visual hero structure paired with download app / install extension CTA and user count, rating, or key metrics.
- Visual summary: Soft & Friendly (Light canvas, balanced density) featuring split copy & visual layout and illustration / character art visuals.

## Avoid

- Harsh pure-black backgrounds
- Sharp 0px corners
- Cold technical jargon in hero copy

Implement the UI following the design tokens and layout specifications above: use only these color variables, and reserve the accent color strictly for primary actions and active states. Adopt only this visual style—never copy any reference product’s brand name, logo, copy, or imagery.

Questions & evidence

How much does Rtrvr.ai cost?
Free: $0; Starter: $9.99/mo (annual billing available); Pro: $29.99/mo (annual billing available); Team: $99.99/mo (annual billing available); Scale: $499.99/mo (annual billing available). Observed 2026-11-04. Check the source for current billing terms, usage limits and taxes.Source
How much website traffic does Rtrvr.ai get?
Vaneform estimates 34.3K website visits in 2026-09. Visits can include repeat visits; this estimate measures web traffic separately from paying customers or revenue.Source
What is Rtrvr.ai and what platforms does it support?
Rtrvr.ai is catalogued under Agent Builders & Platforms: Your free AI browser agent.. Supported platforms: Browser Extension, MCP Server, CLI / SDK, API.
Is Rtrvr.ai open source?
Rtrvr.ai has a public repository (https://github.com/rtrvr-ai/rover) with its source repository published, recording 22 GitHub stars.Source

Related products in this category

AI Models & Agents / Agent Builders & Platforms

These products share a catalog category. Compare customer tasks, features and deployment requirements before treating them as alternatives.