@injaneity: i reverse engineered @OpenAI's Codex Computer Use and built pi-computer-use: a model agnostic computer use tool for my …
Summary
A developer reverse-engineered OpenAI's Codex Computer Use to build pi-computer-use, an open-source, model-agnostic macOS automation tool featuring ax-first navigation and vision fallback for supported models.
View Cached Full Text
Cached at: 04/21/26, 08:28 AM
i reverse engineered @OpenAI’s Codex Computer Use and built pi-computer-use: a model agnostic computer use tool for my fellow pi enjoyers on MacOS. comes with ax-first navigation & a vision fallback for supported models! source code in comments; would love to get some feedback.
Similar Articles
@alading22: Pi community open-sourced the computer-use implementation that Codex did not open-source. After a deep dive into the repository, my eyes lit up!
Pi community open-sourced pi-computer-use, a model-agnostic computer use tool based on reverse engineering OpenAI Codex Computer Use, supporting macOS and visual fallback.
Computer Use in Codex
OpenAI demonstrates the 'Computer Use' feature in Codex, allowing the AI to directly interact with local GUI applications on macOS using an accessibility framework and the fast Spark model for non-blocking, high-speed automation.
Codex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn fro…
OpenAI's Codex has been significantly expanded with new capabilities including macOS app integration, multi-tool connectivity, image generation, action memory, and persistent task automation.
Codex for (almost) everything
OpenAI’s Codex gains Mac app control, tool integration, image generation, memory of user preferences, and the ability to handle ongoing repeatable tasks.
@injaneity: pi-computer-use v0.4.3 is here! an update to bring us to parity with codex (who to their credit, stepped up their game …
pi-computer-use v0.4.3 is released, bringing parity with Codex, adding a ghost cursor, parallel tasks for subagents, and improved batching, resulting in 50% latency improvement and better handling of complex use cases like Microsoft apps.