No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by awlevin · Agent Tool · ★ 573
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is typesafe-computer-use safe to install? View the security audit →
Featured in: TypeSafe Jev
typesafe-computer-use drives a Mac toward a goal you type in plain English, for about a fiftieth of a cent per step. It never sends a screenshot to a big model. Instead it reads the screen deterministically, asks a small classifier which action comes next, and only calls a writing model when a text field genuinely needs free text. Why Frontier-model computer use is capable and expensive: every step ships a s
| Stars | 573 |
| Forks | 34 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 70.5060443364302/100 |
| Open Issues | 8 |
| Last Updated | 2026-09-20 |
| Created | 2026-09-16 |
| Platforms | cli, python |
| Est. Tokens | ~17k |
Looking for a typesafe-computer-use alternative? If you're comparing typesafe-computer-use 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.
Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required.
State of the Art 82% OSWorld Computer Using Agent, production-ready. Remote and Local! Setup using one API Key
Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr
MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron C
471 plugins, 3,069 skills, 347 agents for Claude Code. Open-source marketplace at tonsofskills.com with the cc
Compile a demonstrated GUI workflow into a deterministic, locally executable program. Zero model calls on heal
Explore other popular agent tool tools:
typesafe-computer-use is Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.. It is categorized as a Agent Tool with 573 GitHub stars.
typesafe-computer-use is primarily written in Python. It covers topics such as ai-agents, automation, computer-use.
You can find installation instructions and usage details in the typesafe-computer-use GitHub repository at github.com/awlevin/typesafe-computer-use. The project has 573 stars and 34 forks, indicating an active community.
typesafe-computer-use is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to typesafe-computer-use on Agent Skills Hub include ghost-os, open-computer-use, daymon. 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: