agent-browser

Browser-Automatisierung für KI-Agenten über inference.sh. Navigieren Sie auf Webseiten, interagieren Sie mit Elementen über @e-Referenzen, machen Sie Screenshots, nehmen Sie Video auf. Fähigkeiten: Web Scraping, Formularausfüllen, Klicken, Tippen, Drag & Drop, Datei-Upload, JavaScript-Ausführung. Verwendung für: Web-Automatisierung, Datenextraktion, Testen, Agenten-Browsing, Recherche. Auslöser: Browser, Web-Automatisierung, Scrapen, Navigieren, Klicken, Formular ausfüllen, Screenshot, Web durchsuchen, Playwright, Headless-Browser, Web-Agent, Internet surfen, Video aufnehmen

npx skills add https://github.com/halt-catch-fire/skills --skill agent-browser

Install the belt CLI skill: npx skills add belt-sh/cli

Agentic Browser

Browser automation for AI agents via inference.sh. Uses Playwright under the hood with a simple @e ref system for element interaction.

Agentic Browser

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Open a page and get interactive elements
belt app run agent-browser --function open --input '{"url": "https://example.com"}' --session new

Core Workflow

Every browser automation follows this pattern:

  1. Open - Navigate to URL, get @e refs for elements
  2. Interact - Use refs to click, fill, drag, etc.
  3. Re-snapshot - After navigation/changes, get fresh refs
  4. Close - End session (returns video if recording)
# 1. Start session
RESULT=$(belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com/login"
}')
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
# Elements: @e1 [input] "Email", @e2 [input] "Password", @e3 [button] "Sign In"

# 2. Fill and submit
belt app run agent-browser --function interact --session $SESSION_ID --input '{
  "action": "fill", "ref": "@e1", "text": "user@example.com"
}'
belt app run agent-browser --function interact --session $SESSION_ID --input '{
  "action": "fill", "ref": "@e2", "text": "password123"
}'
belt app run agent-browser --function interact --session $SESSION_ID --input '{
  "action": "click", "ref": "@e3"
}'

# 3. Re-snapshot after navigation
belt app run agent-browser --function snapshot --session $SESSION_ID --input '{}'

# 4. Close when done
belt app run agent-browser --function close --session $SESSION_ID --input '{}'

Functions

FunctionDescription
openNavigate to URL, configure browser (viewport, proxy, video recording)
snapshotRe-fetch page state with @e refs after DOM changes
interactPerform actions using @e refs (click, fill, drag, upload, etc.)
screenshotTake page screenshot (viewport or full page)
executeRun JavaScript code on the page
closeClose session, returns video if recording was enabled

Interact Actions

ActionDescriptionRequired Fields
clickClick elementref
dblclickDouble-click elementref
fillClear and type textref, text
typeType text (no clear)text
pressPress key (Enter, Tab, etc.)text
selectSelect dropdown optionref, text
hoverHover over elementref
checkCheck checkboxref
uncheckUncheck checkboxref
dragDrag and dropref, target_ref
uploadUpload file(s)ref, file_paths
scrollScroll pagedirection (up/down/left/right), scroll_amount
backGo back in history-
waitWait millisecondswait_ms
gotoNavigate to URLurl

Element Refs

Elements are returned with @e refs:

@e1 [a] "Home" href="/"
@e2 [input type="text"] placeholder="Search"
@e3 [button] "Submit"
@e4 [select] "Choose option"
@e5 [input type="checkbox"] name="agree"

Important: Refs are invalidated after navigation. Always re-snapshot after:

  • Clicking links/buttons that navigate
  • Form submissions
  • Dynamic content loading

Features

Video Recording

Record browser sessions for debugging or documentation:

# Start with recording enabled (optionally show cursor indicator)
SESSION=$(belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com",
  "record_video": true,
  "show_cursor": true
}' | jq -r '.session_id')

# ... perform actions ...

# Close to get the video file
belt app run agent-browser --function close --session $SESSION --input '{}'
# Returns: {"success": true, "video": <File>}

Cursor Indicator

Show a visible cursor in screenshots and video (useful for demos):

belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com",
  "show_cursor": true,
  "record_video": true
}'

The cursor appears as a red dot that follows mouse movements and shows click feedback.

Proxy Support

Route traffic through a proxy server:

belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com",
  "proxy_url": "http://proxy.example.com:8080",
  "proxy_username": "user",
  "proxy_password": "pass"
}'

File Upload

Upload files to file inputs:

belt app run agent-browser --function interact --session $SESSION --input '{
  "action": "upload",
  "ref": "@e5",
  "file_paths": ["/path/to/file.pdf"]
}'

Drag and Drop

Drag elements to targets:

belt app run agent-browser --function interact --session $SESSION --input '{
  "action": "drag",
  "ref": "@e1",
  "target_ref": "@e2"
}'

JavaScript Execution

Run custom JavaScript:

belt app run agent-browser --function execute --session $SESSION --input '{
  "code": "document.querySelectorAll(\"h2\").length"
}'
# Returns: {"result": "5", "screenshot": <File>}

Deep-Dive Documentation

ReferenceDescription
references/commands.mdFull function reference with all options
references/snapshot-refs.mdRef lifecycle, invalidation rules, troubleshooting
references/session-management.mdSession persistence, parallel sessions
references/authentication.mdLogin flows, OAuth, 2FA handling
references/video-recording.mdRecording workflows for debugging
references/proxy-support.mdProxy configuration, geo-testing

Ready-to-Use Templates

TemplateDescription
templates/form-automation.shForm filling with validation
templates/authenticated-session.shLogin once, reuse session
templates/capture-workflow.shContent extraction with screenshots

Examples

Form Submission

SESSION=$(belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com/contact"
}' | jq -r '.session_id')

# Get elements: @e1 [input] "Name", @e2 [input] "Email", @e3 [textarea], @e4 [button] "Send"

belt app run agent-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e1", "text": "John Doe"}'
belt app run agent-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e2", "text": "john@example.com"}'
belt app run agent-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e3", "text": "Hello!"}'
belt app run agent-browser --function interact --session $SESSION --input '{"action": "click", "ref": "@e4"}'

belt app run agent-browser --function snapshot --session $SESSION --input '{}'
belt app run agent-browser --function close --session $SESSION --input '{}'

Search and Extract

SESSION=$(belt app run agent-browser --function open --session new --input '{
  "url": "https://google.com"
}' | jq -r '.session_id')

belt app run agent-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e1", "text": "weather today"}'
belt app run agent-browser --function interact --session $SESSION --input '{"action": "press", "text": "Enter"}'
belt app run agent-browser --function interact --session $SESSION --input '{"action": "wait", "wait_ms": 2000}'

belt app run agent-browser --function snapshot --session $SESSION --input '{}'
belt app run agent-browser --function close --session $SESSION --input '{}'

Screenshot with Video

SESSION=$(belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com",
  "record_video": true
}' | jq -r '.session_id')

# Take full page screenshot
belt app run agent-browser --function screenshot --session $SESSION --input '{
  "full_page": true
}'

# Close and get video
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
echo $RESULT | jq '.video'

Sessions

Browser state persists within a session. Always:

  1. Start with --session new on first call
  2. Use returned session_id for subsequent calls
  3. Close session when done

Related Skills

# Web search (for research + browse)
npx skills add inference-sh/skills@web-search

# LLM models (analyze extracted content)
npx skills add inference-sh/skills@llm-models

Documentation

Mehr Skills von halt-catch-fire

agent-tools
halt-catch-fire
Führe 250+ KI-Apps über die inference.sh CLI aus – Bildgenerierung, Videocrstellung, LLMs, Suche, 3D, Twitter-Automatisierung. Modelle: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter und viele mehr. Verwende dies beim Ausführen von KI-Apps, Generieren von Bildern/Videos, Aufrufen von LLMs, Websuche oder Automatisieren von Twitter. Auslöser: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
developmentapicreative
ai-avatar-video
halt-catch-fire
Erstelle KI-Avatar- und Talking-Head-Videos über die inference.sh CLI. Empfohlen: P-Video-Avatar (schnellste, günstigste, integrierte TTS). Auch: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ Sprachen, Emotionssteuerung für Charaktere), ElevenLabs, Kokoro. Fähigkeiten: audiogesteuerte Avatare, Text-zu-Avatar, Lipsync-Videos, Talking-Head-Generierung, virtuelle Präsentatoren, UGC-Inhalte. Verwenden für: KI-Präsentatoren, Erklärvideos, virtuelle Influencer, Synchronisation, Marketingvideos, UGC-Anzeigen, Gaming-Avatare,...
videocreativemedia
ai-image-generation
halt-catch-fire
Generieren Sie KI-Bilder mit GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve und über 50 Modellen über die inference.sh CLI. Modelle: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Fähigkeiten: Text-zu-Bild, Bild-zu-Bild, Inpainting, LoRA, Bildbearbeitung, Hochskalierung, Textrendering. Verwendung für: KI-Kunst, Produkt-Mockups, Konzeptkunst, Social-Media-Grafiken, Marketing-Visuals, Illustrationen. Auslöser: flux, Bildgenerierung, KI-Bild, Text zu...
creativemediaimage
ai-video-generation
halt-catch-fire
Erstelle KI-Videos mit Google Veo, Seedance 2.0, HappyHorse, Wan, Grok und 40+ Modellen über die inference.sh CLI. Modelle: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Fähigkeiten: Text-zu-Video, Bild-zu-Video, Referenz-zu-Video, Videobearbeitung, Lippen-Sync, Avatar-Animation, Video-Upscaling, Foley-Sound. Verwendung für: Social-Media-Videos, Marketinginhalte, Erklärvideos, Produktdemos, KI-Avatare. Auslöser: Videoerstellung, KI-Video,...
creativevideomedia
app-store-screenshots
halt-catch-fire
We need to translate the given text from English to German. The text describes an agent skill for creating App Store and Google Play screenshots with exact platform specs. It includes dimensions, ordering, mockups, preview videos, and lists use cases and triggers. We must preserve the name "app-store-screenshots" but it's not in the text, so we don't include it. We translate only the text inside <text>. No extra labels or commentary. Keep technical terms like "App Store", "Google Play", "iOS", "Android", "ASO", "screenshots", "mockups", etc. as they are or use common German equivalents? "App Store" and "Google Play" are proper names, keep as is. "iOS" and "Android" are standard. "ASO" is an acronym, keep. "screenshots" can be "Screenshots" in German. "mockups" can be "Mockups". "preview videos" -> "Vorschauvideos". "gallery ordering" -> "Galerie-Re
designmarketingcreative
character-design-sheet
halt-catch-fire
We need to translate the given text from English to German. The text is a description of an agent skill for character design. We must preserve the name "character-design-sheet" but it's not in the text, so we ignore. We translate the text inside <text>. No extra labels. Keep technical terms like "LoRA", "turnaround views", "expression sheets", etc. Translate naturally. The text: "Character consistency across AI-generated images with reference sheets and LoRA techniques. Covers turnaround views, expression sheets, color palettes, and style consistency tricks. Use for: character design, game art, illustration, animation, comics, visual novels. Triggers: character design, character sheet, character consistency, character reference, turnaround sheet, expression sheet, character art, consistent character, character concept, reference sheet, character creation, oc design,..." Translation: "Charakterkonsistenz über KI-generierte Bilder hinweg mit Referenzblättern und LoRA-Techniken. Beinhaltet Drehansichten, Ausdrucksblätter, Farb
creativedesignmedia
competitor-teardown
halt-catch-fire
We need to translate the given English text into German. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. The name "competitor-teardown" is to be preserved but only if it appears in the source text. It does appear in the triggers list: "competitor teardown". So we keep that as is. Also "SWOT" is a technical term, keep as is. "UX" is an abbreviation, keep as is. "SWOT analysis" - keep SWOT. "competitive intelligence" might be translated? But instruction says preserve technical terms. "competitive intelligence" is a term, but it's English. However, the target language is German, so we should translate common terms unless they are proper names. The instruction says "preserve product names, protocol names, URLs, numbers, and technical terms." "Competitive intelligence" is a technical term, but it's also a common phrase. I think it's safe to translate it to "Wettbewerbsintelligenz" or keep as is?
researchdata-analysismarketing
image-to-video
halt-catch-fire
We need to translate the given text from English to German. The text is a description of an agent skill for image-to-video conversion. We must preserve the name "image-to-video" but it's not in the text; the text has "Still-to-video conversion guide" etc. We need to translate the entire text inside <text> tags. No extra commentary, no labels. Keep product names, protocol names, URLs, numbers, technical terms. So "Wan 2.5 i2v", "Seedance", "Fabric", "Grok Video" should remain as is. Also "i2v" is a technical term. The triggers list: "image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image" - these are all terms, we should translate the English words that are not proper names? But "image to video" is a common phrase;