ko-browser: A simple, fast, token-efficient browser for AI agents

by libi · Agent Tool · ★ 26

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Security audit verdict: CAUTION · quality 68/100

Flagged: sudo usage. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

agentagent-browserai-browser-automationai-browser-controlbrowserbrowser-use-agent

Quick Facts

Stars26
Forks1
LanguageGo
CategoryAgent Tool
LicenseMIT
Quality Score68/100
Last Updated2026-04-15
Created2026-03-31
Platformsbrowser, go
Est. Tokens~21k

About ko-browser

A simple, fast, token-efficient browser for AI agents

ko-browser alternative? Top 5 similar tools

Looking for a ko-browser alternative? If you're comparing ko-browser with other agent tool tools, these 5 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • vscode-mcp by tjx666 · ⭐ 103

    MCP server for Claude Code/VSCode/Cursor/Windsurf to use editor self functionality. ⚡ Get real-time LSP diagno

  • evoui-browser by Salmonbird · ⭐ 100

    Self-evolving browser automation for Codex, Claude Code, and Cursor—learn reusable site knowledge and safely r

  • SweetCookieKit by steipete · ⭐ 98

    Extract browser cookies from macOS in Swift

  • gemini-browser-agent by pmbstyle · ⭐ 76

    A browser agent with a Google Chrome extension that can work in your browser. Based on Google Gemini 2.5 compu

  • spel by Blockether · ⭐ 71

    Idiomatic Clojure wrapper for Playwright. Browser automation, API testing, Allure reporting, and native CLI -

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Go Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools