Skip to main content
This domain is for sale. Contact Snagged to learn more.
SC

Open-source browser agent for completing web tasks from plain-language prompts

Scout is a TypeScript browser-agent SDK that reads pages and autonomously clicks, types, scrolls, and extracts answers for multi-step web tasks. Developers can run it with a local Playwright browser or Outcrawl’s hosted browser service, while supplying their own chat-completions-compatible AI models.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 11 November 2026.

See pricing ↓

Web Browsing
B2B
Computer Use
Cloud Hosted
Self-Hosted
Fully Autonomous
Visit Scout

Is this your tool? Claim this listing to manage your content and analytics.

Ask about Scout

Get answers based on Scout's actual documentation

Try asking:

About

What It Is

Scout is an open-source browser automation agent from Outcrawl for developers who want to turn natural-language tasks into browser actions. You give it a task such as researching a site, comparing products, filling a form, or signing in; it uses a...

What to Know

Scout is genuinely agentic: it can execute multi-step browser workflows rather than merely suggesting steps. Its separate model roles let developers trade off speed and capability—for example, using a fast model for page actions and an image-capable...

Key Features
Executes browser tasks from natural-language instructions
Uses a real browser to click, type, scroll, read pages, and sign in
Returns results in a developer-defined JSON Schema
Supports separate `hands`, `brain`, `eyes`, and `extract` model roles
Works with chat-completions-compatible hosted, gateway, or local model endpoints
Use Cases
Researching a site and returning the top stories, links, and comment counts in a fixed structure
Comparing product prices and stock across pages before reporting the lower-priced option
Completing an online form and reporting the submitted details
Agenticness: Adaptive Collaborator

Proposes and executes multi-step plans with your approval.

High evidence
Last evaluated: Nov 11, 2026
This tool has strong action capabilities but limited safety controls. Use with appropriate oversight.

Dimension Breakdown

Action Capability
Autonomy
Planning
Adaptation
State & Memory
Reliability
Interoperability
Safety
Operator Sovereignty

Categories

Pricing

Free and open source (Apache-2.0). Running locally with Playwright costs nothing beyond your own model calls. Cloud runs use Outcrawl's hosted browser and are billed as Outcrawl browser sessions; every Outcrawl account gets 1,000 free credits a month, no card needed.

Details
AddedNovember 11, 2026
RefreshedNovember 11, 2026
Quick Facts
DeploymentHybrid (cloud + self-hosted)
AutonomyFully autonomous
Model supportSupports local models
Open sourceYes
Team supportIndividual only
Pricing modelFree / open source
Interfaceapi, cli
Sources
Last updated November 11, 2026
Free daily brief

When Scout changes its pricing, we catch it the next morning

We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.

I use AI for: