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 screenshot and waits several seconds for a plan. Most steps do not need a plan. They need one choice from a short list, made quickly and cheaply, with a confidence number you can gate on.
| Stars | 1,244 |
| Forks | 119 |
| Language | Python |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 69.71909475477/100 |
| Open Issues | 41 |
| Last Updated | 2026-09-29 |
| Created | 2026-09-16 |
| Platforms | cli, python |
| Est. Tokens | ~17k |
Explore other popular ai 工具 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 AI 工具 with 1.2k 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 1.2k stars and 119 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.