GitHub - puffinsoft/mousecrack: Imitate human mouse movement with deep learning. · GitHub
/" data-turbo-transient="true" />
Skip to content
Type / to search
Sign in<br>Sign upAppearance settings
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
Uh oh!
There was an error while loading. Please reload this page.
puffinsoft
mousecrack
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star<br>65
master
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>36 Commits<br>36 Commits
.claude-plugin
.claude-plugin
.codex-plugin
.codex-plugin
assets
assets
inference
inference
skills/move-mouse
skills/move-mouse
train
train
.gitignore
.gitignore
LICENSE
LICENSE
README.md
README.md
View all files
Repository files navigation
Synthesize organically varied, human-like mouse movement.
This project aims to test the abilities of deep-learning for mouse imitation.
See it in Action
demo.mp4
Installation
npm i -g mousecrack
Usage
Warning<br>This project is still experimental! For educational purposes only.
Available as an SDK (for developers) and CLI (for agents).
SDK
import { move, steps } from 'mousecrack';
await move(200, 400);
// or alternatively...<br>const from = { x: 100, y: 200 }<br>const to = { x: 200, y: 400 }<br>await steps(from, to);
// [<br>// { x: 100, y: 200, t: 0 },<br>// { x: 95, y: 202, t: 10.528131778472712 },<br>// { x: 90, y: 210, t: 21.040190062833986 },<br>// { x: 81, y: 223, t: 31.892832399406224 },<br>// ...
CLI
mousecrack move 200 400 # (x, y)<br>mousecrack steps 100 200 200 400 # from (x, y), to (x, y)
Install the Skill<br>For Claude Code:
/plugin marketplace add puffinsoft/mousecrack<br>/plugin install move-mouse@mousecrack
For Codex:
codex plugin marketplace add puffinsoft/mousecrack<br>codex plugin add move-mouse@mousecrack
📌 Choosing Models
To support all hardware systems, we develop two models- Standard (2x128 LSTM) and Lite (2x64 LSTM).
Append lite or standard as a parameter to each CLI command to choose:
mousecrack move 200 400 lite # or standard<br>mousecrack steps 100 200 200 400 lite # or standard
And with the SDK:
import { ModelType, move, steps } from 'mousecrack';
await move(200, 400, ModelType.LITE);<br>await steps(from, to, ModelType.LITE);
Caution<br>Lite is not recommended, unless your hardware forces you to.
It performs inference, on average, 29% faster, but the end-to-end generation time can take up to 8x as long.
This is because the smaller model tends to veer off course more often.
How does it work?
Mousecrack treats mouse prediction like a time forecasting problem.
It models mouse movement as a change in position (dx, dy) and time (dt), and tries to predict the next step in this multivariate time series.
To avoid the mode collapse problem, Mousecrack uses a Mixture Density Network to model several trajectories as a probability distribution.
Mousecrack is open source software, licensed under the MIT license.
About<br>Imitate human mouse movement with deep learning.<br>Resources<br>Readme<br>MIT license<br>Activity<br>Custom properties<br>Stars<br>65 stars<br>Watchers<br>0 watching<br>Forks<br>4 forks<br>Report repository
Releases
Packages
Contributors
Languages
You can’t perform that action at this time.