Cua Driver Adds Privacy-Conscious Cross-Session Action History
- Source
- x.com
- Date
1/ Today, we're releasing the first open-source Computer History - now in early preview for Cua Driver on macOS, Windows, and Linux. It gives agents an encrypted, local record of actions they took through Cua Driver, so new sessions can recover useful context from earlier work.
2/ An agent's chat history helps within one conversation. Computer History survives a reset, a new session, or a different compatible agent. The agent can query which apps and Cua capabilities were used and whether actions succeeded. It still asks when the user's intent is missing.
3/ Test prompt on macOS: “Move the white pawn from e2 to e4.” With history off, the agent tried three routes that failed. With history on, it reused the successful route, completed the task with 33.3% fewer actions, and had no failed routes.
4/ Test prompt on Windows: “Continue the prior Paint task after context was reset.” Computer History gave the agent app attribution, the prior action sequence, and confirmed outcomes. It did not store the drawing, screenshots, typed text, raw arguments, titles, or paths.
Context
Cua released an early preview of Computer History for Cua Driver on macOS, Windows and Linux: an encrypted, local record of actions an took through Cua Driver, so a new session, a reset or a different compatible agent can recover . Unlike chat history, which helps within one conversation, it survives those changes.
It records fixed metadata such as session lifecycle, Cua actions, target app identity and outcomes. Cua says it excludes screenshots, typed text, keystrokes, clipboard contents, window titles, URLs, raw arguments and results, accessibility trees and paths. History stays on the computer, encrypted before it reaches disk with a key in the operating system's credential store, and no history event or content enters product telemetry.
In Cua's macOS test of moving a chess pawn, the agent with history off tried three failed routes; with it on, it reused the successful route and used 33.3% fewer actions. That is a single Cua-reported test. The feature is off by default and currently needs the nightly channel.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Checking sign-in…
Loading comments…