agent-browser

Automação de navegador para agentes de IA via inference.sh. Navegue por páginas da web, interaja com elementos usando referências @e, tire capturas de tela, grave vídeo. Capacidades: raspagem web, preenchimento de formulários, cliques, digitação, arrastar e soltar, upload de arquivos, execução de JavaScript. Use para: automação web, extração de dados, testes, navegação por agente, pesquisa. Gatilhos: navegador, automação web, raspar, navegar, clicar, preencher formulário, captura de tela, navegar na web, playwright, navegador headless, agente web, surfar na internet, gravar vídeo

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

Mais skills de halt-catch-fire

agent-tools
halt-catch-fire
Execute mais de 250 aplicativos de IA via CLI do inference.sh - geração de imagens, criação de vídeos, LLMs, busca, 3D, automação do Twitter. Modelos: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter e muitos outros. Use ao executar aplicativos de IA, gerar imagens/vídeos, chamar LLMs, fazer busca na web ou automatizar o Twitter. Gatilhos: 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
Crie vídeos de avatar com IA e vídeos de cabeça falante via CLI do inference.sh. Recomendado: P-Video-Avatar (mais rápido, mais barato, TTS integrado). Também: OmniHuman, Fabric, PixVerse. Áudio: Inworld TTS-2 (mais de 100 idiomas, controle de emoção para personagens), ElevenLabs, Kokoro. Capacidades: avatares guiados por áudio, texto para avatar, vídeos com sincronia labial, geração de cabeça falante, apresentadores virtuais, conteúdo UGC. Use para: apresentadores de IA, vídeos explicativos, influenciadores virtuais, dublagem, vídeos de marketing, anúncios UGC, avatares de jogos,...
videocreativemedia
ai-image-generation
halt-catch-fire
Gere imagens de IA com GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve e mais de 50 modelos via CLI do inference.sh. Modelos: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capacidades: texto para imagem, imagem para imagem, inpainting, LoRA, edição de imagem, upscaling, renderização de texto. Use para: arte de IA, mockups de produtos, arte conceitual, gráficos para redes sociais, visuais de marketing, ilustrações. Gatilhos: flux, geração de imagem, imagem de IA, texto para...
creativemediaimage
ai-video-generation
halt-catch-fire
We need to translate the given text from English to Brazilian Portuguese. The text describes an AI video generation skill. We must preserve the name "ai-video-generation" but it's not in the text, so we ignore. Preserve product names, protocol names, URLs, numbers, technical terms. So we keep: Google Veo, Seedance 2.0, HappyHorse, Wan, Grok, inference.sh CLI, Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo, text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound, social media videos, marketing content, explainer videos, product demos, AI avatars, video generation, ai video. Also numbers like 40+ models, 1.0, 2.5, etc. Translate the rest naturally. The
creativevideomedia
app-store-screenshots
halt-catch-fire
Criação de capturas de tela para App Store e Google Play com especificações exatas das plataformas. Abrange dimensões iOS/Android, ordenação da galeria, mockups de dispositivos e vídeos de pré-visualização. Use para: otimização na App Store, ASO, capturas de tela de apps, pré-visualização de apps, listagem na Play Store. Gatilhos: capturas de tela da App Store, aso, otimização na App Store, capturas de tela da Play Store, pré-visualização de apps, listagem de apps, capturas de tela iOS, capturas de tela Android, imagens da App Store, mockup de app, mockup de dispositivo, galeria de apps, listagem na loja
designmarketingcreative
character-design-sheet
halt-catch-fire
Consistência de personagens em imagens geradas por IA com folhas de referência e técnicas LoRA. Abrange vistas de rotação, folhas de expressão, paletas de cores e truques de consistência de estilo. Use para: design de personagens, arte de jogos, ilustração, animação, quadrinhos, romances visuais. Gatilhos: design de personagem, ficha de personagem, consistência de personagem, referência de personagem, folha de rotação, folha de expressão, arte de personagem, personagem consistente, conceito de personagem, folha de referência, criação de personagem, design de OC,...
creativedesignmedia
competitor-teardown
halt-catch-fire
Análise competitiva estruturada com matrizes de funcionalidades, SWOT, mapas de posicionamento e revisão de UX. Abrange frameworks de pesquisa, comparação de preços, mineração de avaliações e entregáveis visuais. Use para: pesquisa de mercado, inteligência competitiva, apresentações para investidores, estratégia de produto, capacitação de vendas. Gatilhos: análise de concorrente, análise competitiva, desmontagem de concorrente, pesquisa de mercado, inteligência competitiva, análise swot, comparação de concorrentes, panorama de mercado, revisão de concorrente, competitivo...
researchdata-analysismarketing
image-to-video
halt-catch-fire
We need to translate the given text from English to Brazilian Portuguese. The text is a description of an agent skill for image-to-video conversion. The name "image-to-video" is in the directory item type but not in the text, so we don't include it. The text includes product names like Wan 2.5 i2v, Seedance, Fabric, Grok Video - these should be preserved as is. Also technical terms like "i2v" should remain. The translation should be natural in Brazilian Portuguese. Let's translate: "Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: 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