Tell Claude, Cursor, or Copilot to test your app and write a guide — automatically. Or record manually, track bugs and feature requests, analyze issues, and export visual docs. Free, privacy-first Chrome extension with 50+ MCP tools.
Sentinel replaces scattered tools with one lightweight extension. Use it manually or connect your AI assistant via MCP with 50+ tools to fully automate testing and documentation.
Captures clicks, typing, scrolls, form submissions, and navigation automatically with intelligent noise reduction, smart selectors, and candidate fallbacks.
Replay recorded sessions at 0.5x to 4x speed with selector recovery and heuristic matching. Step-by-step mode pauses after each action with element highlighting.
Add assertions with configurable retry logic — visible, hidden, text-contains, text-equals, has-class, or exists. Get pass/fail test reports with flakiness detection.
Turn recordings into polished HTML guides with embedded screenshots. Add custom sections, choose internal or client export profiles, and use the block-based renderer for full control.
Auto-capture console errors, network failures, and CSP violations. Analyze issues with duplicate detection, clustering, and severity levels. Export styled reports with full error context.
Create feature requests tied to specific page elements. Inspect an element, describe the enhancement, set priority, and export — all with screenshots and DOM context.
Capture up to 5 minutes of video per clip as WebM. Download clips or attach them to your bug reports for clear reproduction.
50+ MCP tools let Claude, Cursor, or Copilot navigate, record, query elements, capture screenshots, drag-and-drop, compare screenshots, and export guides — fully hands-free.
Add manual notes with tagging and project tracking. Use the PowerPoint-style editor to annotate screenshots with pens, shapes, arrows, and text. Double-click to edit, drag to move, and manage layers.
Organize testing by project with descriptions and repository links. View all aggregated screenshots, videos, and findings in a centralized Resource Gallery per workspace.
No setup, no accounts, no configuration files. Install, open the side panel, and start recording.
Click the record button and interact with your web app. Sentinel captures every action with smart selectors and screenshots.
Browse your recorded steps in the side panel. Each step shows what happened, where, and when — with a screenshot.
Add assertions, then play back the session. Sentinel simulates every action and evaluates your assertions, producing a test report.
Generate a standalone HTML guide, an issue report, or download a video clip. Share with your team — no logins needed.
Whether you're a solo developer or part of a QA team, Sentinel fits your workflow.
Record critical user flows, add assertions, and run regression playback before every release. Export test reports as evidence that paths work.
Walk through your app once and export a visual step-by-step guide. New team members get screenshots and descriptions instead of outdated wikis.
Enable error tracking, reproduce the bug, and export an issue report with screenshots, console errors, and network failures attached.
Record a walkthrough of completed features and export an HTML guide. Clients see exactly what was built — no staging environment needed.
Point your AI at a project folder and say "test the checkout flow and write a guide." Claude Code, Cursor, or Copilot navigate, query elements, drag-and-drop, compare screenshots, and export — hands-free via 50+ MCP tools.
Run a quick AI investigation on your dev server to surface JS errors and network failures before opening a PR. Get a screenshot + error report in seconds, with issue clustering and duplicate detection.
Choose your preferred installation method.
Read the full user guide to get started — from manual recording to AI-driven automation via MCP.
Sentinel is free and open source. If it saves you time, consider sponsoring the project ♥