Rankings/GenericAgent

GenericAgent

lsdefine/GenericAgent

This is a self-evolving AI assistant that automatically accumulates skills by executing tasks, helping you automate computer and phone operations, getting smarter with use without complex setup.

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

Stars
4,048
Forks
426
Watchers
14
Issues
42
💡

This is a self-evolving AI assistant that automatically accumulates skills by executing tasks, helping you automate computer and phone operations, getting smarter with use without complex setup.

📂 AI & Automation🤖 AI Related💻 Python📄 MIT

AI Summary

🔍

What This Project Does

This is a self-evolving AI agent with only 3000 lines of core code, capable of directly controlling your computer and phone to automatically complete various tasks.

🔧

What Problems It Solves

Solves the problem of low efficiency in manual repetitive operations on computers and phones, replacing tedious script writing, letting AI automatically learn and remember your operation habits.

👥

Who It's For

Suitable for geeks wanting to improve efficiency, office workers needing automated office work, and developers willing to try new technologies.

📋

Typical Use Cases

Automatically ordering milk tea, monitoring stock market trends and alerting, batch sending WeChat messages, automatically browsing web pages and summarizing content.

Key Strengths & Highlights

Gets smarter with use, tasks automatically crystallize into skills after completion; Low token consumption, low cost; No complex deployment, strong system-level control.

🚀

Getting Started Requirements

Requires Python environment, need to configure Large Model API Key, initial run requires minor debugging, but subsequent use is simple.

🎯

Purpose

Suitable for those wanting to automate daily chores and having some technical foundation, not for those unwilling to tinker with environments.

Tech Stack

Project Info

Primary Language
Python
Default Branch
main
License
MIT
Created
Jan 16, 2026
Last Commit
1 months ago
Last Push
1 months ago
Indexed
Apr 18, 2026