What Tablif read on Agentic Web Check's site
- Price model: free tier
- Free tier: Free forever
- Stage: Live, no waitlist
- Alternative to: Lighthouse
- How it differs: “What it adds: checks at the level of what an agent perceives in a live browser”
What it is
Calls itself “browser evaluator”.
- Calls itself: browser evaluator
“Open-source browser evaluator for AI agents.”
Where it puts itself
Positions itself as an alternative to Lighthouse. Claims “no open-source tool that runs a browser agent through site-generic tasks and emits verdicts with failure attribution”. Rules out “telemetry”.
- Alternative to: Lighthouse
- Superlative claim: no open-source tool that runs a browser agent through site-generic tasks and emits verdicts with failure attribution
- Says it will not: telemetry
“What it adds: checks at the level of what an agent perceives in a live browser (unnamed and fake controls, overlays, hover-only menus, closed shadow roots, canvas-only UIs, bot walls), behavioural tasks with evidence-backed verdicts, and a safety review aimed at site owners.”
“Why not just Lighthouse Lighthouse 13.x ships an official Agentic Browsing category”
What it costs
A free tier, free forever.
- Free plan: free forever
“Open-source browser evaluator for AI agents.”
Who it sells to
Sells to developers.
- Sells to: developers
“Safety review aimed at site owners.”
How it runs
A command-line tool. Runs locally and works offline. Distributed through the npm. No API. Open source. AI is the core of the product. You can bring your own API key.
- Kind: cli
- Runs where: on the device, offline
- Distributed via: npm
- API: no
- Open source: yes
- AI role: core to the product
- Bring your own key: yes
“Local CLI, no telemetry.”
“It runs locally with no telemetry.”
What it works with
Names Anthropic, Chrome DevTools MCP and 4 more on its pages.
- Names: Anthropic · Chrome DevTools MCP · Lighthouse · +3
“Open-source browser evaluator for AI agents. Agentic Web Check combines 43 deterministic checks with real read-only browser tasks”
“Anthropic Messages API. Configure with AWC_LLM_PROVIDER ( openai | anthropic )”
What it offers as proof
Live, no waitlist. Try it without signing up. Publishes docs.
- Trial asks for: nothing
“…npx agentic-web-check scan https://example.com # no install”
“…docs -> https://github.com/ericovirgy/agentic-web-check/tree/main/docs”
Sources
Tablif read these pages, last on 6 Oct 2026. Everything above is what the product says about itself; Tablif does not verify every claim.
Similar products in Tablif Town
- AI based Website Check : Website Intelligence – 10 AI agents analyze your website
- Scalebrowser: Human browser capabilities. Now for AI agents.
- SanityCheck: AI Agents test your application like real users.
- robotcheck: Score your website's readability for AI crawlers and search bots
- Agentic Visibility Score: Measure and improve your product visibility for AI search
- Agent Interface: Give AI agents a better way to use computers
- Agent Activity: See what your AI agents do behind
- AgentSearch: Web search, extract and render for AI agents, pay per call