What did Hlido score pinchtab/pinchtab?

pinchtab/pinchtab scored 82/100 (STEADY) in Hlido's independent, hands-on review.

How much does pinchtab/pinchtab cost?

Hlido recorded the pricing model as: Open source. Derived from evidence Hlido holds, not vendor-supplied; verify current prices on the vendor's pricing page.

Does any vendor pay Hlido for placement?

No. Hlido takes no money from the agents it rates — scoring weights stay private and the evidence behind every verdict is public.

pinchtab/pinchtab

Name: pinchtab/pinchtab review
Item: pinchtab/pinchtab
Rating: 82
Author: Hlido Editor

Infrastructure · tested 2026-09-24 · by the Hlido desk, not the vendor

In short: A purpose-built browser-control bridge for AI agents — small Go binary, HTTP API, stealth injection — that reads as genuinely agent-first, though its heavier claims sit behind self-hosting.

10 PASS · 0 FAIL of 10 public-surface claims

Visit pinchtab/pinchtab → scorecard.json

Quick answer

pinchtab/pinchtab scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-09-24). STEADY reflects a healthy, actively maintained open-source repo (license, CI, releases, recent commits, documented install) whose value proposition is coherent and genuinely agent-oriented. Pricing: Open source (free entry point documented).

Hlido Editor · 2026-09-24

PinchTab is a standalone HTTP server that gives an AI agent direct control over Chrome, shipped as a small Go binary with a token-efficient API and a real-time dashboard. That framing — "browser control for AI agents" rather than "browser automation" repackaged for agents — is the right one, and the repository backs it with the signals Hlido can verify from the public surface: an Apache-2.0 license, Go CI, tagged releases, and recent commits. Where it gets interesting, and riskier, is the stealth-injection and multi-instance orchestration story. Anti-detection browser tooling is a legitimate need for agents that hit bot-walled sites, but it also invites misuse, and the project is candid that remote/distributed layouts are advanced operator-managed deployments you must lock down yourself. As a self-hosted component this is a capable building block; it is not a managed service, so the operational burden — securing endpoints, staying within target sites' terms — falls entirely on the deployer. For teams already running headless-Chrome fleets it is a credible, lighter-weight alternative to a full Playwright grid.

Why STEADY

STEADY reflects a healthy, actively maintained open-source repo (license, CI, releases, recent commits, documented install) whose value proposition is coherent and genuinely agent-oriented. It is not rated higher because the review is a public-surface + repo-health assessment (medium confidence) — Hlido did not run the binary against live targets — and the stealth/anti-detection posture carries operational and misuse risk the buyer must own.

Public-surface checklist

PASS Repo reachable (required) — GH API 200 for pinchtab/pinchtab
PASS Readme present (required) — README length 16038
PASS License present (required) — MIT
PASS Install documented (required) — install/usage section found in README
PASS Active 12mo (required) — last push 1d ago
PASS Releases present — latest v0.14.1
PASS Community traction — 9426 stars
PASS Ci or tests — 23 workflow file(s)
PASS Recent commit 90d — last push 1d ago
PASS Agent consumable — MCP server markers in README

What we saw

1 screenshot captured by the Hlido engine during the reviewed run (run-280d34327e0c32af-github-com). Our own captures — not vendor marketing material.

pinchtab/pinchtab — run screenshot 1 (home.png) — home.png

What it does well

Agent-first design: a plain HTTP API over Chrome, explicitly built for AI agents rather than retrofitted
Small, dependency-light Go binary — low operational footprint versus a full browser-automation stack
Apache-2.0 licensed with visible Go CI and tagged releases (real maintenance signals)
Token-efficient interface, which matters when an LLM is driving the browser loop
Honest documentation about the advanced/operator-managed nature of remote deployments

What it fails at

Stealth/anti-detection framing invites terms-of-service and misuse questions the project pushes onto the operator
Self-hosted only — no managed option, so security hardening is the deployer's responsibility
Public surface is a GitHub repo; there is no browsable live demo to verify behaviour pre-adoption
Multi-instance orchestration and distributed layouts are documented as advanced, not turnkey
Hlido's automated pass could not execute the binary, so runtime reliability is asserted by the project, not independently confirmed here

Red flags

Stealth-injection and anti-detection capabilities can be used to evade site protections; the project places responsibility for lawful use on the operator, which is honest but leaves the risk with the buyer.

Best for

Builders wiring an AI agent to real browser control who want a lightweight, self-hosted bridge
Teams comfortable operating and securing their own headless-Chrome infrastructure
Go shops that prefer a single binary over a Node/Playwright dependency tree
Agent workflows that need token-efficient page control at scale

Not recommended for

Teams wanting a managed, zero-ops browser-automation service
Anyone who needs a vendor to own the compliance/anti-abuse posture of stealth browsing
Buyers who require a live, pre-signup demo before committing
Use cases where target sites' terms forbid automated/stealth access

Pricing & access

ModelOpen source
Free entry pointYes — a free tier or open-source edition is documented

Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-07-16.

Related agents

Agent relevance

API CLI Behavioral-testable

Agentic-Commerce Readiness 54/100 · INTEGRABLE

Independent readiness for agent delegation & transaction. How it’s scored · check live

Exposes an HTTP API that an agent calls directly to drive Chrome; runs as a local/self-hosted server. No MCP server, but the plain HTTP surface is straightforward to wrap. Purpose-built for agent consumption.

Agent-friendly score: 8/10

Evidence

Public repository reachable with substantive README — source (2026-09-24) verified
Product description: "High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time" — source (2026-09-24) verified
Open-source license present in repository — source (2026-09-24) verified

scorecard.json · transparency passport · registry · methodology

More: compare agents · best of · developer tools · incident registry

Verdict by Hlido Editor, our automated editorial system · Method: public-surface+repo-health-tier-2+editorial-narrative-v2 · Methodology version 2026.09 ·

How this page was produced. The scores, claim verdicts and evidence come from automated hands-on testing of the product’s public surface. The written analysis is drafted by an AI system, and pages publish without a person reviewing each one. Hlido publishes this record and answers for it — tell us if anything here is wrong and we will correct it.

Embed this trust badge

Live, always-current independent score — free to embed on your site or README. No vendor pays for placement.

Markdown

[![Hlido trust score](https://hlido.eu/badge/pinchtab-pinchtab.svg)](https://hlido.eu/check/?agent=pinchtab-pinchtab)

HTML

<a href="https://hlido.eu/check/?agent=pinchtab-pinchtab"><img src="https://hlido.eu/badge/pinchtab-pinchtab.svg" alt="Hlido trust score"></a>