Scout

brew install klarlabs-studio/tap/scout

# CLI — visible browser, one-shot commands
scout observe https://example.com          # structured page snapshot
scout markdown https://news.ycombinator.com # page as compact markdown
scout screenshot https://github.com         # save screenshot
scout extract https://example.com h1        # extract element text
scout frameworks https://react.dev          # detect React, Vue, etc.

# MCP Server — give AI agents browser superpowers
claude mcp add scout -- scout mcp serve

# Browser UI — conversational browser automation
scout ui serve --provider=ollama --model=mistral
cd ui && npm install && npm run dev  # open http://localhost:3000

# Homebrew
brew install klarlabs-studio/tap/scout

# Direct binary
curl -fsSL https://raw.githubusercontent.com/klarlabs-studio/scout/main/install.sh | bash

# Go
go install go.klarlabs.de/scout/cmd/scout@latest

# As a library
go get go.klarlabs.de/scout

claude mcp add scout -- scout mcp serve           # Claude Code

{"mcpServers": {"scout": {"command": "scout", "args": ["mcp", "serve"]}}}

Agent: configure(headless: false)                        → browser window appears
Agent: navigate("https://...")                           → watch it work
Agent: configure(headless: true)                         → back to headless
Agent: configure(allow_private_ips: true)                → unlock localhost / 192.168.* / 10.*
Agent: navigate("http://127.0.0.1:4173/")                → drive your local dev server

Agent: start_screen_recording({ width: 1280, height: 800, fps: 15, format: "webm" })
Agent: navigate("https://example.com")
Agent: click("#cta")
Agent: navigate("https://example.com/dashboard")   # recording continues across pages
Agent: stop_screen_recording()
       → { path: "/tmp/scout-rec-XXX.webm", format: "webm", encoder: "ffmpeg",
           frame_count: N, duration_ms: N }

# Start the AG-UI server (Go backend)
scout ui serve --provider=ollama --model=mistral    # local, no API key
scout ui serve --provider=claude                     # needs ANTHROPIC_API_KEY
scout ui serve --provider=openai --model=gpt-4o     # needs OPENAI_API_KEY
scout ui serve --provider=groq --base-url=https://api.groq.com/openai --model=llama-3.3-70b-versatile

# Start the Vue frontend
cd ui && npm install && npm run dev                  # http://localhost:3000

session, _ := agent.NewSession(agent.SessionConfig{Headless: true})
defer session.Close()

// Navigate and observe
session.Navigate("https://example.com")
obs, _ := session.Observe()               // links, inputs, buttons, text + action costs

// DOM diff — only what changed (saves 50-80% tokens)
session.Click("#submit")
_, diff, _ := session.ObserveDiff()
// diff.Classification: "modal_appeared"
// diff.Summary: "Modal/dialog appeared: Login required"

// Semantic form filling — no CSS selectors
session.FillFormSemantic(map[string]string{
    "Email": "user-example", "Password": "secret",
})

// Visual grounding — click by number, not selector
result, _ := session.AnnotatedScreenshot()  // numbered labels on elements
session.ClickLabel(7)                        // click element [7]

// Multi-tab coordination
session.OpenTab("pricing", "https://example.com/pricing")
session.SwitchTab("default")

// Framework detection (19 frameworks)
frameworks, _ := session.DetectedFrameworks() // ["react", "nextjs"]
state, _ := session.ComponentState("#app")    // read React/Vue state

// Network capture — read API responses directly
session.EnableNetworkCapture("/api/")
captured := session.CapturedRequests("/api/users")

// Action replay — record once, replay without LLM
session.StartRecordingPlaybook("login-flow")
// ... do stuff ...
pb, _ := session.StopRecordingPlaybook()
agent.SavePlaybook(pb, "login.json")
// Later: session.ReplayPlaybook(pb)  // 100x cheaper

// Persistent profiles
session.SaveProfile("session.json")   // cookies + localStorage
session.LoadProfile("session.json")

// Content distillation (5 levels)
session.Markdown()          // ~2-8KB compact markdown
session.ReadableText()      // ~1-4KB main content only
session.AccessibilityTree() // ~1-4KB semantic tree
session.ObserveWithBudget(500) // fit in ~500 tokens

engine := browse.Default(browse.WithHeadless(true))
engine.MustLaunch()
defer engine.Close()

engine.Use(middleware.Stealth())
engine.Use(middleware.Retry(middleware.RetryConfig{MaxAttempts: 3}))
engine.Use(middleware.Timeout(30 * time.Second))

admin := engine.Group("admin", middleware.BasicAuth("admin", "secret"))
admin.Task("export", func(c *browse.Context) {
    c.MustNavigate("https://app.example.com/admin")
    table, _ := c.ExtractTable("#users")
    c.Set("data", table)
})

engine.RunGroup("admin")

scout navigate <url>                  # page info as JSON
scout observe <url>                   # structured observation
scout markdown <url>                  # compact markdown
scout readable <url>                  # main readable content (boilerplate stripped)
scout accessibility <url>             # semantic accessibility tree
scout screenshot <url> [--output f]   # save screenshot
scout pdf <url> [--output f]          # save PDF
scout extract <url> <selector>        # extract text
scout table <url> <selector>          # extract a table as structured rows
scout auto-extract <url>              # auto-detect dominant data pattern
scout eval <url> <expression>         # run JavaScript
scout form discover <url>             # discover form fields
scout frameworks <url>                # detect frameworks
scout app-state <url>                 # global app/store state (JSON)
scout aria <url>                      # ARIA violation report (JSON)
scout vitals <url>                    # Core Web Vitals (JSON)
scout console <url>                   # console errors + network 4xx/5xx (JSON)
scout dialog <url>                    # detect visible modal/dialog (JSON)
scout auth-wall <url>                 # detect login/auth wall (JSON)
scout cookies <url>                   # list cookies (values redacted)
scout watch <url> [--interval=5s]     # live-watch page changes
scout pipe <command> [selector]       # batch process URLs from stdin
scout record <url> [--output f]       # interactive recording → playbook
scout mcp serve                       # start MCP server
scout ui serve [flags]                # start chat UI
scout version                         # print version

scout/
├── browse.go, engine.go, context.go   # Gin-like API
├── page.go, selection.go              # CDP page & element interaction
├── recorder.go                        # Action playbook recording (Navigate/Click/Type → JSON)
├── middleware/                        # stealth, resilience, auth, network
├── agent/                             # AI agent API (50+ methods)
│   ├── session.go                     # Session lifecycle, Navigate, Click, Type
│   ├── observe.go, diff.go            # Observe, ObserveDiff, cost estimation
│   ├── content.go                     # Markdown, ReadableText, AccessibilityTree
│   ├── form.go                        # DiscoverForm, FillFormSemantic, MatchFormField
│   ├── annotate.go                    # AnnotatedScreenshot, ClickLabel
│   ├── network.go                     # EnableNetworkCapture, CapturedRequests
│   ├── spa.go                         # DetectedFrameworks, ComponentState, GetAppState
│   ├── tabs.go                        # OpenTab, SwitchTab, CloseTab, ListTabs
│   ├── playbook.go                    # StartRecording, ReplayPlaybook, SavePlaybook
│   ├── interact.go                    # Hover, DragDrop, SelectOption, ScrollTo
│   ├── profile.go                     # CaptureProfile, ApplyProfile, SaveProfile
│   ├── selector.go                    # Playwright :text() selector translation
│   ├── budget.go                      # ObserveWithBudget, EstimateTokens
│   ├── nlselect.go                    # SelectByPrompt, fuzzy NL element matching
│   ├── batch.go                       # ExecuteBatch, sequential multi-action
│   ├── vision.go                      # HybridObserve, FindByCoordinates
│   ├── trace.go                       # StartTrace, StopTrace, action tracing
│   ├── screencast.go                  # StartScreenRecording / StopScreenRecording — video via captureScreenshot polling + ffmpeg encode
│   ├── iframe.go                      # SwitchToFrame, SwitchToMainFrame
│   └── vitals.go                      # WebVitals (LCP/CLS/INP)
├── internal/cdp/                      # WebSocket CDP client (context-aware)
├── internal/launcher/                 # Chrome process management
├── cmd/scout/                         # CLI + MCP server (87 tools)
└── docs/                              # Landing page (GitHub Pages)

# Local scan
nox scan -severity-threshold high .

# Local fix
nox fix -input findings.json