lsdefine / GenericAgent

English | 中文 --- 🌟 Overview **GenericAgent** is a minimal, self-evolving autonomous agent framework. Its core is just **~3,300 lines of code**. Through **7 atomic tools + a 92-line Agent Loop**, it grants any LLM system-level control over a local computer — covering browser, terminal, filesystem, keyboard/mouse input, screen vision, and mobile devices (ADB). Its design philosophy: **don't preload skills — evolve them.** Every time GenericAgent solves a new task, it automatically crystallizes the execution path into an skill for direct reuse later. The longer you use it, the more skills accumulate — forming a skill tree that belongs entirely to you, grown from 3,300 lines of seed code. > **🤖 Self-Bootstrap Proof** — Everything in this repository, from installing Git and running to every commit message, was completed autonomously by GenericAgent. The author never opened a terminal once. 📋 Core Features • **Self-Evolving**: Automatically crystallizes each task into an skill. Capabilities grow with every use, forming your personal skill tree. • **Minimal Architecture**: ~3,300 lines of core code. Agent Loop is just 92 lines. No complex dependencies, zero deployment overhead. • **Strong Execution**: Injects into a real browser (preserving login sessions). 7 atomic tools take direct control of the system. • **High Compatibility**: Supports Claude / Gemini / Kimi and other major models. Cross-platform. 🧬 Self-Evolution Mechanism This is what fundamentally distinguishes GenericAgent from every other agent framework. | What you say | What the agent does the first time | Every time after | |---|---|---| | *"Read my WeChat messages"* | Install deps → reverse DB → write read script → save skill | **one-line invoke** | | *"Monitor stocks and alert me"* | Install mootdx → build selection flow → configure cron → save skill | **one-line start** | | *"Send this file via Gmail"* | Configure OAuth → write send script → save skill | **ready to use** | After a few weeks, your agent instance will have a skill tree no one else in the world has — all grown from 3,300 lines of seed code. 🎯 Demo Showcase | 🧋 Food Delivery Order | 📈 Quantitative Stock Screening | |:---:|:---:| | | | | *"Order me a milk tea"* — Navigates the delivery app, selects items, and completes checkout automatically. | *"Find GEM stocks with EXPMA golden cross, turnover > 5%"* — Screens stocks with quantitative conditions. | | 🌐 Autonomous Web Exploration | 💰 Expense Tracking | 💬 Batch Messaging | | | | | | Autonomously browses and periodically summarizes web content. | *"Find expenses over ¥2K in the last 3 months"* — Drives Alipay via ADB. | Sends bulk WeChat messages, fully driving the WeChat client. | 📅 Latest News • **2026-03-23:** Support personal WeChat as a bot frontend • **2026-03-10:** Released million-scale Skill Library • **2026-03-08:** Released "Dintal Claw" — a GenericAgent-powered government affairs bot • **2026-03-01:** GenericAgent featured by Jiqizhixin (机器之心) • **2026-01-11:** GenericAgent V1.0 public release --- 🚀 Quick Start Method 1: Standard Installation Method 2: Windows Portable Version (Recommended for beginners) Download portable version (19MB, unzip and run) Full guide: WELCOME_NEW_USER.md Method 3: Android (Termux) --- 🤖 Bot Interfaces (Optional) QQ Bot Uses WebSocket long connection — **no public webhook required**: Add to : > Create a bot at the QQ Open Platform to get AppID / AppSecret. After the first message, user openid is logged in . Lark (Feishu) **Inbound support**: text, rich text post, images, files, audio, media, interactive cards / share cards **Outbound support**: streaming progress cards, image replies, file / media replies **Vision model**: Images are sent as true multimodal input to OpenAI Vision-compatible backends on the first turn Full setup: assets/SETUP_FEISHU.md WeCom (Enterprise WeChat) DingTalk Telegram Bot 📊 Comparison with Similar Tools | Feature | GenericAgent | OpenClaw | Claude Code | |------|:---:|:---:|:---:| | **Codebase** | ~3,300 lines | ~530,000 lines | Open-sourced (large) | | **Deployment** | + API Key | Multi-service orchestration | CLI + subscription | | **Browser Control** | Real browser (session preserved) | Sandbox / headless browser | Via MCP plugin | | **OS Control** | Mouse/kbd, vision, ADB | Multi-agent delegation | File + terminal | | **Self-Evolution** | Autonomous skill growth | Plugin ecosystem | Stateless between sessions | | **Out of the Box** | 10 .py files + 5 skills | Hundreds of modules | Rich CLI toolset | 🧠 How It Works GenericAgent accomplishes complex tasks through **Layered Memory × Minimal Toolset × Autonomous Execution Loop**, continuously accumulating experience during execution. 1️⃣ **Layered Memory System** > _Memory crystallizes throughout task execution, letting the agent build stable, efficient working patterns over time._ • **L0 — Meta Rules**: Core behavioral rules and system constraints of the agent • **L2 — Global Facts**: Stable knowledge accumulated over long-term operation • **L3 — Task Skillss**: Workflows for completing specific task types 2️⃣ **Autonomous Execution Loop** > _Perceive environment state → Task reasoning → Execute tools → Write experience to memory → Loop_ The entire core loop is just **92 lines of code** ( ). 3️⃣ **Minimal Toolset** > _GenericAgent provides only **7 atomic tools**, forming the foundational capabilities for interacting with the outside world._ | Tool | Function | |------|------| | | Execute arbitrary code | | | Read files | | | Write files | | | Patch / modify files | | | Perceive web content | | | Control browser behavior | | | Human-in-the-loop confirmation | > Additionally, 2 **memory management tools** ( , ) allow the agent to persist context and accumulate experience across sessions. 4️⃣ **Capability Extension Mechanism** > _Capable of dynamically creating new tools._ Via , GenericAgent can dynamically install Python packages, write new s…