by aduermael · Agent Tool · ★ 65
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
macOS 26+ browser CLI for agents: persistent sessions, compact JSON, screenshots, clicks/forms, JS eval, and live preview in under 2 MB.
| Stars | 65 |
| Forks | 2 |
| Language | Swift |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 51.8460768631138/100 |
| Last Updated | 2026-07-08 |
| Created | 2026-06-20 |
| Platforms | browser, cli |
| Est. Tokens | ~15k |
Looking for a wb alternative? If you're comparing wb with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
CLI tool for agents to quickly access browser telemetry (DOM, network, console) via Chrome DevTools Protocol.
Static analysis tool that catches 1000+ bug patterns across all popular programming languages, with auto-wirin
Personal Assistant Wizard for Claude Code — npx pawmode
MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron C
A unified CLI for discovering and invoking tools across OpenAPI, MCP, GraphQL, gRPC, and JSON-RPC
Clipboard Manager for macOS
Explore other popular agent tool tools:
wb is macOS 26+ browser CLI for agents: persistent sessions, compact JSON, screenshots, clicks/forms, JS eval, and live preview in under 2 MB.. It is categorized as a Agent Tool with 65 GitHub stars.
wb is primarily written in Swift. It covers topics such as agent-tools, ai-agents, automation.
You can find installation instructions and usage details in the wb GitHub repository at github.com/aduermael/wb. The project has 65 stars and 2 forks, indicating an active community.
wb is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to wb on Agent Skills Hub include browser-debugger-cli, ultimate_bug_scanner, openpaw. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: