jackwener/OpenCLI
Workflow & Automation · tested 2026-08-27 · by the Hlido desk, not the vendor
In short: Turns any website — plus browser sessions, Electron and local tools — into a deterministic CLI for humans and AI agents, and runs Browser Use on your logged-in Chrome. A genuinely agent-shaped idea.
3 PASS · 2 FAIL of 5 public-surface claims
Quick answer
jackwener/OpenCLI scores 75/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-08-27). STEADY (75). Pricing: Open source (free entry point documented).
OpenCLI aims squarely at a real agent pain point: web surfaces are non-deterministic and login-gated, so it wraps them as deterministic command-line interfaces an agent can drive, and can run Browser Use against your already-authenticated Chrome. The value proposition is clear on the public surface and it ships as an npm package with a documentation homepage. What the public surface doesn't settle is depth: there's no visible pricing or hard call-to-action (expected for an open-source tool), and we could not verify hands-on how robustly the "any website" promise holds across messy real-world pages — that is exactly the kind of claim that degrades on the long tail. Promising for agent builders who want deterministic, logged-in web access without standing up their own browser harness; validate on your specific target sites before depending on it.
Why STEADY
STEADY (75). A clear, differentiated, agent-native value proposition, an npm distribution and a documentation homepage clear STEADY. VITAL is withheld because the breadth claim ("any website") is unverified hands-on and the public surface alone cannot confirm robustness across real-world pages.
Public-surface checklist
- PASS Homepage loads (required)
- PASS Primary value prop (required)
- FAIL Cta present (required)
- FAIL Pricing or access
- PASS Evidence or demo
What we saw
1 screenshot captured by the Hlido engine during the reviewed run (run-419e46f8bb96e7fd-github-com). Our own captures — not vendor marketing material.
What it does well
- Wraps arbitrary websites, browser sessions, Electron and local tools as deterministic CLIs
- Runs Browser Use against a logged-in Chrome — reuses existing authenticated sessions
- Explicitly designed for both humans and AI agents (deterministic interfaces)
- Distributed on npm with a documentation homepage
What it fails at
- The "any website" breadth claim is unverified on the long tail of messy pages
- No hands-on behavioral confirmation of robustness
- Public surface shows no clear call-to-action or usage limits
Best for
- Agent builders needing deterministic, logged-in web access
- Automations that must reuse an authenticated browser session
- Developers wrapping internal web tools as agent-drivable interfaces
Not recommended for
- Users needing a guaranteed, tested success rate across arbitrary sites
- Non-technical users wanting a no-code automation product
Pricing & access
- ModelOpen source
- Free entry pointYes — a free tier or open-source edition is documented
- Pricing findable on the public surfaceFAIL
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 2026-06-14.
Compared to
-
Browser Use
deterministic CLI wrapping
Browser Use is the general browser-automation agent library OpenCLI actually builds on; OpenCLI adds the "wrap any site as a deterministic CLI" layer and the logged-in-Chrome path on top. Choose Browser Use for the underlying automation primitive; choose OpenCLI when you want deterministic command interfaces over existing, authenticated web tools.
Agent relevance
API CLI SDK Behavioral-testable
Agentic-Commerce Readiness 48/100 · SURFACE-ONLY
Independent readiness for agent delegation & transaction. How it’s scored · check live
Installable CLI/npm package that exposes websites and local tools as deterministic commands an agent can invoke, plus Browser Use over a logged-in browser. Behaviorally testable in principle; not tested hands-on for this review.
Agent-friendly score: 8/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
