Releases: remorses/usecomputer
usecomputer@0.1.3
-
Kitty Graphics Protocol support —
screenshotnow emits the PNG inline to stdout using the Kitty Graphics Protocol. SetAGENT_GRAPHICS=kittyand the image lands directly in the AI model's context window — no separate file-read step needed:AGENT_GRAPHICS=kitty usecomputer screenshot ./shot.png --json # { ..., "agentGraphics": true }Works with kitty-graphics-agent, an OpenCode plugin that intercepts the escape sequences and injects them as LLM-visible image attachments. Add to
opencode.json:{ "plugin": ["kitty-graphics-agent"] } -
Aligned table output for list commands —
display list,window list, anddesktop listnow render as aligned, human-readable tables. JSON mode (--json) is unchanged. -
Fixed
agentGraphicsJSON field — the field now reflects actual Kitty emission success. Empty PNG files and I/O errors correctly reportfalse.
usecomputer@0.1.1
- Fixed Linux native builds — standalone executable now links libc correctly, fixing "C allocator is only available when linking against libc" errors
- Fixed native host builds — build script omits
-Dtargetwhen building for the host platform so Zig finds system libraries (X11, libpng, etc)
usecomputer@0.1.0
-
Standalone executable — ships as a self-contained binary, no Node.js required at runtime
-
Linux X11 screenshot support — capture screens on Linux via XShm with XGetImage fallback on XWayland
-
Screenshot coord-map and scaling — longest edge scaled to 1568 px with
coordMapfield for accurate pointer remapping:usecomputer screenshot ./shot.png --json usecomputer click -x 400 -y 220 --coord-map "0,0,1600,900,1568,882" -
New
debug-pointcommand — draw a red marker at a mapped coordinate to validate clicks before executing:usecomputer debug-point -x 400 -y 220 --coord-map "0,0,1600,900,1568,882" -
Keyboard synthesis —
typeandpresscommands for text input and key chords:usecomputer type "hello from usecomputer" usecomputer press "cmd+s" cat ./notes.txt | usecomputer type --stdin --chunk-size 4000
-
Native scroll support — scroll in any direction at any screen position:
usecomputer scroll --direction down --amount 5
-
Library exports — import as a Node.js library for use in custom agent harnesses:
import * as usecomputer from 'usecomputer' const shot = await usecomputer.screenshot({ path: './shot.png', display: null, window: null, region: null, annotate: null })
-
OpenAI and Anthropic computer-use examples — README includes full agentic loop examples for both providers