jevbooks

← All projects

anonymous-browser

frederico-kluser/anonymous-browser · Homepage

Disposable Tor browser with rotating fingerprint, driven by AI agents.

Automated README summary

Automatically summarized from the README on 27 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A disposable, isolated browser with Tor-rotated IP and coherent C++-level fingerprint spoofing, for humans and AI agents. One command installs Tor, Camoufox and a Python venv; the same package is an agent skill that navigates autonomously from a prompt.

How it uses Jev

Jev (TypeSafe typesafe/jev-1.13 via OpenRouter Decisions endpoint) decides each step: one call per step, it picks the operation (click, type, wait, open e-mail, done…) and target, and returns calibrated probabilities for "goal met?", "stuck?", "prompt injection?" and "irreversible action? does the goal authorize it?".

Primitives:choicescore

Technique worth stealing

Give the model a short table of actionable viewport controls plus visible text instead of raw HTML, so typed decisions stay cheap and calibrated.

Try it

npm i -g anonymous-browser; anonymous-browser agent run "…" --url …

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectnot found in the excerpt0.29
  • Shows a System One patternunclear0.60
  • Describes handling uncertaintyFound in material0.65
  • Reports measured numbersnot found in the excerpt0.03
  • Is a runnable toolFound in material0.98
  • Top-10 learning shortlist signalnot found in the excerpt0.23
  • Is a replica of the modelnot found in the excerpt0.10
  • Solves a common problem (0–2)score on a 0–2 scale1.02 / 2
  • About JevFound in material0.69
Signals
Jev is core to the project0.29Shows a System One pattern0.60Describes handling uncertainty0.65Reports measured numbers0.03Is a runnable tool0.98Top-10 learning shortlist signal0.23Is a replica of the model0.1000.51Solves a common problem (0–2)1.02 / 2012

no-judgment band (0.40–0.60)

Design patterns
Ghostwriter0.98Blind review0.88Fail open, fail closed0.73Funnel0.65Flight recorder0.64Menu0.59Traffic light0.55Questionnaire0.34Viewfinder0.32Thermostat0.2300.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 27 Sept 2026.