lsdefine / GenericAgent

Official channel: This GitHub repository is the sole official source for GenericAgent. We have no affiliation with any third-party website using the GenericAgent name.

官方渠道： 本 GitHub 仓库是 GenericAgent 的唯一官方来源。我们与任何使用 GenericAgent 名称的第三方网站均无关联。

🌟 Overview

GenericAgent is a minimal, self-evolving autonomous agent framework. Its core is just ~3K lines of code. Through 9 atomic tools + a ~100-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 a 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 3K lines of seed code.

🌟 项目概述

GenericAgent 是一个极简的、可自我进化的自主智能体框架。其核心代码仅约 3000 行。通过 9 个原子工具和约 100 行的 Agent Loop（智能体循环），它赋予了任何大模型（LLM）对本地计算机的系统级控制能力——涵盖浏览器、终端、文件系统、键鼠输入、屏幕视觉以及移动设备（ADB）。其设计理念是：不预装技能，而是进化技能。每当 GenericAgent 完成一项新任务，它会自动将执行路径固化为一项技能，以便后续直接复用。使用时间越长，积累的技能就越多，从而形成一个完全属于你个人的技能树，而这一切都源自那 3000 行种子代码。

🤖 Self-Bootstrap Proof

Everything in this repository, from installing Git and running git init to every commit message, was completed autonomously by GenericAgent. The author never opened a terminal once.

🤖 自举证明

本仓库中的一切，从安装 Git 和运行 git init 到每一条提交信息，均由 GenericAgent 自主完成。作者从未手动打开过一次终端。

📋 Core Features

Self-Evolving: Automatically crystallizes each task into a skill. Capabilities grow with every use, forming your personal skill tree.
Minimal Architecture: ~3K lines of core code. Agent Loop is ~100 lines. No complex dependencies, zero deployment overhead.
Strong Execution: Injects into a real browser (preserving login sessions). 9 atomic tools take direct control of the system.
High Compatibility: Supports Claude / Gemini / Kimi / MiniMax and other major models. Cross-platform.
Token Efficient: <30K context window — a fraction of the 200K–1M other agents consume. Layered memory ensures the right knowledge is always in scope. Less noise, fewer hallucinations, higher success rate — at a fraction of the cost.

📋 核心功能

自我进化： 自动将每项任务固化为技能。能力随使用而增长，形成你的个人技能树。
极简架构： 核心代码约 3000 行，Agent Loop 仅约 100 行。无复杂依赖，零部署负担。
强大执行力： 注入真实浏览器（保留登录会话）。9 个原子工具直接接管系统控制权。
高兼容性： 支持 Claude / Gemini / Kimi / MiniMax 等主流模型，且跨平台。
Token 高效： 上下文窗口小于 30K，仅为其他智能体（200K–1M）的一小部分。分层记忆确保相关知识始终在作用域内。更少的噪音、更少的幻觉、更高的成功率，且成本更低。

🧬 Self-Evolution Mechanism

This is what fundamentally distinguishes GenericAgent from every other agent framework. [New Task] —> [Autonomous Exploration] (install deps, write scripts, debug & verify) —> [Crystallize Execution Path into skill] —> [Write to Memory Layer] —> [Direct Recall on Next Similar Task]

🧬 自我进化机制

这是 GenericAgent 与其他所有智能体框架的根本区别所在。 [新任务] —> [自主探索]（安装依赖、编写脚本、调试与验证） —> [将执行路径固化为技能] —> [写入记忆层] —> [下次遇到类似任务时直接调用]

🎯 Demo Showcase

Food Delivery Order: “Order me a milk tea” — Navigates the delivery app, selects items, and completes checkout automatically.
Quantitative Stock Screening: “Find GEM stocks with EXPMA golden cross, turnover > 5%” — Screens stocks with quantitative conditions.
Autonomous Web Exploration: Autonomously browses and periodically summarizes web content.
Expense Tracking: “Find expenses over ¥2K in the last 3 months” — Drives Alipay via ADB.

🎯 演示展示

外卖点餐： “帮我点杯奶茶”——自动导航至外卖 App，选择商品并完成结算。
量化选股： “查找 EXPMA 金叉且换手率大于 5% 的创业板股票”——根据量化条件筛选股票。
自主网页浏览： 自主浏览网页并定期总结内容。
支出追踪： “查找过去 3 个月超过 2000 元的支出”——通过 ADB 驱动支付宝进行查询。

📅 Latest News

2026-04-21: 📄 Technical Report released on arXiv — GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization
2026-04-11: Introduced L4 session archive memory and scheduler cron integration
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)
2026-01-16: GenericAgent V1.0 public release

📅 最新动态

2026-04-21: 📄 技术报告发布于 arXiv — 《GenericAgent：通过上下文信息密度最大化实现 Token 高效的自我进化 LLM 智能体》
2026-04-11: 引入 L4 会话归档记忆和定时任务（cron）集成
2026-03-23: 支持个人微信作为机器人前端
2026-03-10: 发布百万级技能库
2026-03-08: 发布“数字爪”（Dintal Claw）——一款由 GenericAgent 驱动的政务机器人
2026-03-01: GenericAgent 被“机器之心”报道
2026-01-16: GenericAgent V1.0 正式发布

🚀 Quick Start

GenericAgent is meant to grow its environment through the Agent itself, not by pre-installing every possible package. Full guide: GETTING_STARTED.md

🚀 快速开始

GenericAgent 的设计初衷是通过智能体自身来扩展环境，而不是预先安装所有可能的软件包。完整指南请参考：GETTING_STARTED.md