From db0c86167f8065bd7a784dd717151c149babe835 Mon Sep 17 00:00:00 2001 From: Jinyi Han <15224975562@163.com> Date: Mon, 18 May 2026 08:24:50 +0800 Subject: [PATCH] update the readme file (#409) --- README.md | 774 +++++++++++++++++++++++++++++++++--------------------- 1 file changed, 477 insertions(+), 297 deletions(-) diff --git a/README.md b/README.md index aa8c62bd..cc90fe5e 100644 --- a/README.md +++ b/README.md @@ -1,83 +1,118 @@
- -lsdefine%2FGenericAgent | Trendshift +GenericAgent Banner + +# GenericAgent + +**A Minimal, Self-Evolving Autonomous Agent Framework** + +*~3K lines of seed code · 9 atomic tools · ~100-line Agent Loop* + +

+ + Technical Report + Reproduction Repo + Tutorial + Sophub +

+ +

+ Trendshift +

+ +**[English](#-english) · [中文](#-中文)**
-

- English | 中文 | 📄 Technical Report: arXiv Technical Report PDF Experiments & Reproduction Repo | 📘 教程 | Sophub -

- -> 📌 **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. +> 📌 **Official Channel** — This GitHub repository is the **only** official source of GenericAgent. +> We have no affiliation with any third-party website using the GenericAgent name. --- - + + + ## 🌟 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.** +> 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 3K lines of seed code. +Every time GenericAgent solves a new task, it automatically crystallizes the execution path into a reusable **Skill**. The longer you use it, the more skills accumulate — forming a personal skill tree grown entirely from 3K lines of seed code. -> **🤖 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. +> 🤖 **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. -## 📋 Core Features -- **Self-Evolving**: Automatically crystallizes each task into an 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. +### 📑 Table of Contents +- [Key Features](#-key-features) +- [Demo Showcase](#-demo-showcase) +- [Quick Start](#-quick-start) +- [Usage](#-usage) +- [Architecture](#-architecture) +- [Self-Evolution Mechanism](#-self-evolution-mechanism) +- [Comparison](#-comparison) +- [Evaluation](#-evaluation) +- [Roadmap & News](#-roadmap--news) +- [Community & Support](#-community--support) +- [License](#-license) -## 🧬 Self-Evolution Mechanism +--- -This is what fundamentally distinguishes GenericAgent from every other agent framework. +## 📋 Key Features -``` -[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] -``` +| Feature | Description | +| :--- | :--- | +| 🧬 **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. Less noise, fewer hallucinations, higher success rate, lower cost. | -| 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 3K lines of seed code. +## 🎯 Demo Showcase - -##### 🎯 Demo Showcase - -| 🧋 Food Delivery Order | 📈 Quantitative Stock Screening | -|:---:|:---:| -| Order Tea | Stock Selection | -| *"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 | -| Web Exploration | Alipay Expense | WeChat Batch | -| 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 - -- **2026-05-15:** 🖥️ Desktop GUI released — one-line installs now ship a ready-to-run desktop app (`frontends/GenericAgent.exe`), while developers can launch it with `python launch.pyw`. -- **2026-05-14:** 🆕 **Conductor sub-agent orchestration** — spawn, supervise, and auto-clean parallel sub-agents; first-class delegation primitives complementing `/btw` side-questions. -- **2026-05-12:** 🆕 **TUI v2 released** (`frontends/tuiapp_v2.py`) — refined Textual frontend with image-paste folding, file paste, block-delete, Ctrl+C copy, history navigation, and `/llm` / `/export` / `/continue` pickers. -- **2026-04-21:** 📄 [Technical Report released on arXiv](https://arxiv.org/abs/2604.17091) — *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](https://mp.weixin.qq.com/s/q2gQ7YvWoiAcwxzaiwpuiQ?scene=1&click_id=7) -- **2026-03-08:** [Released "Dintal Claw" — a GenericAgent-powered government affairs bot](https://mp.weixin.qq.com/s/eiEhwo-j6S-WpLxgBnNxBg) -- **2026-03-01:** [GenericAgent featured by Jiqizhixin (机器之心)](https://mp.weixin.qq.com/s/uVWpTTF5I1yzAENV_qm7yg) -- **2026-01-16:** GenericAgent V1.0 public release + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
🧋 Food Delivery Order📈 Quantitative Stock Screening
Order TeaStock Selection
"Order me a milk tea" — navigates the delivery app, selects items, completes checkout."Find GEM stocks with EXPMA golden cross, turnover > 5%" — quantitative screening.
🌐 Autonomous Web Exploration💰 Expense Tracking
Web ExplorationAlipay Expense
Autonomously browses and periodically summarizes web content."Find expenses over ¥2K in the last 3 months" — drives Alipay via ADB.
💬 Batch Messaging
WeChat Batch
Sends bulk WeChat messages, fully driving the WeChat client.
--- ## 🚀 Quick Start -> ⚠️ **Python version:** use **Python 3.11 or 3.12**. **Do not** use Python 3.14 — it is incompatible with `pywebview` and a few other GA dependencies. - +> ⚠️ **Python version**: use **Python 3.11 or 3.12**. **Do not** use Python 3.14 — it is incompatible with `pywebview` and a few other GA dependencies. +> > 📖 Detailed installation guide: **[installation.md](docs/installation.md)** · **[installation_zh.md（中文）](docs/installation_zh.md)** ### For LLM Agents @@ -90,7 +125,7 @@ curl -fsSL https://raw.githubusercontent.com/lsdefine/GenericAgent/refs/heads/ma ### For Humans -#### Method 1: One-line install (recommended) +#### Method 1 — One-line install *(recommended)* This installs GenericAgent with an isolated Python environment and Git, then downloads a ready-to-run package. @@ -112,26 +147,28 @@ After installation, launch the desktop app from: frontends/GenericAgent.exe ``` -#### Method 2: Python install (for developers) +#### Method 2 — Python install *(for developers)* ```bash git clone https://github.com/lsdefine/GenericAgent.git cd GenericAgent uv venv -uv pip install -e ".[ui]" # Core + UI dependencies -cp mykey_template.py mykey.py # Fill in your LLM API key +uv pip install -e ".[ui]" # Core + UI dependencies +cp mykey_template.py mykey.py # Fill in your LLM API key python launch.pyw ``` -> GenericAgent is meant to grow its environment through the Agent itself, not by pre-installing every possible package. +> 💡 GenericAgent is meant to grow its environment **through the Agent itself**, not by pre-installing every possible package. -Full guide: [GETTING_STARTED.md](docs/GETTING_STARTED.md) +📖 Full guide: [`docs/GETTING_STARTED.md`](docs/GETTING_STARTED.md) --- -## 🖥️ Frontends +## 💻 Usage -### Desktop App +### Frontends + +#### Desktop App For one-line installs on Windows, double-click: @@ -139,7 +176,7 @@ For one-line installs on Windows, double-click: frontends/GenericAgent.exe ``` -### Terminal UI +#### Terminal UI A lightweight, keyboard-driven interface built on [Textual](https://github.com/Textualize/textual). Supports multiple concurrent sessions and real-time streaming. @@ -147,66 +184,153 @@ A lightweight, keyboard-driven interface built on [Textual](https://github.com/T python frontends/tuiapp_v2.py ``` -> **Windows TUI troubleshooting.** TUI rendering on Windows can be flaky depending on terminal + font. Common causes: -> 1. `textual` is not on the latest version — `pip install -U textual` first. -> 2. PowerShell / cmd ship with terminals that have rough Unicode + key-binding support. **Prefer Git Bash on Windows**, which is much better behaved. -> 3. If it still looks broken, ask GA itself to fix it: -> > *"My experience using `frontends/tuiapp_v2.py` in PowerShell / cmd / Git Bash on Windows is very poor — lots of incompatibility. Please refer to Claude Code's best practices for the Windows terminal and fix all font and rendering incompatibilities."* +
+⚠️ Windows TUI Troubleshooting -### Streamlit UI +TUI rendering on Windows can be flaky depending on terminal + font. Common causes: + +1. `textual` is not on the latest version — `pip install -U textual` first. +2. PowerShell / cmd ship with terminals that have rough Unicode + key-binding support. **Prefer Git Bash on Windows**, which is much better behaved. +3. If it still looks broken, ask GA itself to fix it: + > *"My experience using `frontends/tuiapp_v2.py` in PowerShell / cmd / Git Bash on Windows is very poor — lots of incompatibility. Please refer to Claude Code's best practices for the Windows terminal and fix all font and rendering incompatibilities."* + +
+ +#### Streamlit UI ```bash python launch.pyw ``` ---- - -## 💬 Bot Interface (IM) +### Bot Interface (IM) GenericAgent also supports IM frontends such as Telegram, WeChat, QQ, Feishu / Lark, WeCom, and DingTalk. -Typical usage: +| Platform | Command | +| :--- | :--- | +| Telegram | `python frontends/tgapp.py` | +| WeChat | `python frontends/wechatapp.py` | +| QQ | `python frontends/qqapp.py` | +| Feishu / Lark | `python frontends/fsapp.py` | +| WeCom | `python frontends/wecomapp.py` | +| DingTalk | `python frontends/dingtalkapp.py` | -```bash -python frontends/tgapp.py # Telegram -python frontends/wechatapp.py # WeChat -python frontends/qqapp.py # QQ -python frontends/fsapp.py # Feishu / Lark -python frontends/wecomapp.py # WeCom -python frontends/dingtalkapp.py # DingTalk +> For detailed setup, ask GenericAgent itself. + +### Common Chat Commands + +| Command | Description | +| :--- | :--- | +| `/new` | Start a fresh conversation and clear the current context | +| `/continue` | List recoverable conversation snapshots | +| `/continue N` | Restore the `N`-th recoverable conversation | + +--- + +## 🧠 Architecture + +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.* + +| Layer | Name | Description | +| :---: | :--- | :--- | +| **L0** | Meta Rules | Core behavioral rules and system constraints | +| **L1** | Insight Index | Minimal memory index for fast routing and recall | +| **L2** | Global Facts | Stable knowledge accumulated over long-term operation | +| **L3** | Task Skills / SOPs | Reusable workflows for completing specific task types | +| **L4** | Session Archive | Archived task records distilled from finished sessions for long-horizon recall | + +### 2️⃣ Autonomous Execution Loop + +> *Perceive environment state → Task reasoning → Execute tools → Write experience to memory → Loop* + +The entire core loop is just **~100 lines of code** ([`agent_loop.py`](agent_loop.py)). + +### 3️⃣ Minimal Toolset + +> *GenericAgent provides only **9 atomic tools**, forming the foundational capabilities for interacting with the outside world.* + +| Tool | Function | +| :--- | :--- | +| `code_run` | Execute arbitrary code (Python / PowerShell) | +| `file_read` | Read files | +| `file_write` | Write / create / overwrite files | +| `file_patch` | Patch / modify files | +| `web_scan` | Perceive web content | +| `web_execute_js` | Control browser behavior | +| `ask_user` | Human-in-the-loop confirmation | +| `update_working_checkpoint` | *(memory)* Short-term working notepad | +| `start_long_term_update` | *(memory)* Distill long-term memory | + +### 4️⃣ Capability Extension + +> *Capable of dynamically creating new tools.* + +Via `code_run`, GenericAgent can dynamically install Python packages, write new scripts, call external APIs, or control hardware at runtime — crystallizing temporary abilities into permanent tools. + +
+ GenericAgent Workflow +
GenericAgent Workflow Diagram +
+ +--- + +## 🧬 Self-Evolution Mechanism + +This is what fundamentally distinguishes GenericAgent from every other agent framework. + +```text +[New Task] + │ + ▼ +[Autonomous Exploration] ─► install deps · write scripts · debug · verify + │ + ▼ +[Crystallize into Skill] ─► write to memory layer + │ + ▼ +[Direct Recall on Next Similar Task] ``` -For detailed setup, ask GenericAgent itself. +| What you say | 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** | -Common chat commands: +After a few weeks, your agent instance will have a skill tree no one else in the world has — all grown from 3K lines of seed code. -- `/new` - start a fresh conversation and clear the current context -- `/continue` - list recoverable conversation snapshots -- `/continue N` - restore the `N`th recoverable conversation +--- -## 📊 Comparison with Similar Tools +## 📊 Comparison -| Feature | GenericAgent | OpenClaw | Claude Code | -|------|:---:|:---:|:---:| +| Feature | **GenericAgent** | OpenClaw | Claude Code | +| :--- | :---: | :---: | :---: | | **Codebase** | ~3K lines | ~530,000 lines | Open-sourced (large) | | **Deployment** | `pip install` + 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** | A few core files + starter skills | Hundreds of modules | Rich CLI toolset | +| **Out of the Box** | Few core files + starter skills | Hundreds of modules | Rich CLI toolset | +--- -## 📈 Evaluation — Five Dimensions +## 📈 Evaluation -> 📂 Full evaluation datasets and results: +> 📂 Full evaluation datasets and results: [**JinyiHan99/GA-Technical-Report**](https://github.com/JinyiHan99/GA-Technical-Report/tree/main) -| Dimension | Question | Benchmarks used | -|---|---|---| -| **1. Task Completion & Token Efficiency** | Can GA complete hard tasks more cheaply than leading agents? | SOP-Bench, Lifelong AgentBench, RealFin-Benchmark | -| **2. Tool-Use Efficiency** | Can a minimal atomic toolset solve what specialized toolsets solve, with less overhead? | Tool Efficiency Benchmark (11 simple + 5 long-horizon tasks) | -| **3. Memory System Effectiveness** | Does condensed hierarchical memory beat full/redundant memory and embedding-based retrievers? | SOP-Bench (dangerous goods), LoCoMo, 20-skill stress test | -| **4. Self-Evolution Capability** | Can the agent distill experience into reusable SOPs and code, without intervention? | 9-round LangChain longitudinal study, 8-task cross-task web benchmark | -| **5. Web Browsing Capability** | Does density-driven design survive the open web? | WebCanvas, BrowseComp-ZH, Custom Tasks (22) | +We evaluate GenericAgent across **five dimensions**: + +| # | Dimension | Question | Benchmarks | +| :---: | :--- | :--- | :--- | +| 1 | **Task Completion & Token Efficiency** | Can GA complete hard tasks more cheaply than leading agents? | SOP-Bench, Lifelong AgentBench, RealFin-Benchmark | +| 2 | **Tool-Use Efficiency** | Can a minimal atomic toolset solve what specialized toolsets solve, with less overhead? | Tool Efficiency Benchmark (11 simple + 5 long-horizon) | +| 3 | **Memory System Effectiveness** | Does condensed hierarchical memory beat full/redundant memory and embedding-based retrievers? | SOP-Bench (dangerous goods), LoCoMo, 20-skill stress test | +| 4 | **Self-Evolution Capability** | Can the agent distill experience into reusable SOPs and code, without intervention? | 9-round LangChain longitudinal study, 8-task cross-task web benchmark | +| 5 | **Web Browsing Capability** | Does density-driven design survive the open web? | WebCanvas, BrowseComp-ZH, Custom Tasks (22) | Baselines across these dimensions include **Claude Code**, **OpenAI CodeX**, and **OpenClaw**, evaluated under *Claude Sonnet 4.6*, *Claude Opus 4.6*, *GPT-5.4*, and *MiniMax M2.7* backbones. @@ -223,152 +347,142 @@ Baselines across these dimensions include **Claude Code**, **OpenAI CodeX**, and +--- -## 🧠 How It Works +## 📅 Roadmap & News -GenericAgent accomplishes complex tasks through **Layered Memory × Minimal Toolset × Autonomous Execution Loop**, continuously accumulating experience during execution. +- **2026-05-15** — 🖥️ **Desktop GUI released**. One-line installs ship a ready-to-run desktop app (`frontends/GenericAgent.exe`). Developers launch via `python launch.pyw`. +- **2026-05-14** — 🆕 **Conductor sub-agent orchestration**. Spawn, supervise, and auto-clean parallel sub-agents; first-class delegation primitives complementing `/btw` side-questions. +- **2026-05-12** — 🆕 **TUI v2 released** (`frontends/tuiapp_v2.py`). Refined Textual frontend with image-paste folding, file paste, block-delete, Ctrl+C copy, history navigation, and `/llm` / `/export` / `/continue` pickers. +- **2026-04-21** — 📄 [**Technical Report on arXiv**](https://arxiv.org/abs/2604.17091) — *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** — Personal WeChat supported as a bot frontend. +- **2026-03-10** — [Released million-scale Skill Library](https://mp.weixin.qq.com/s/q2gQ7YvWoiAcwxzaiwpuiQ?scene=1&click_id=7). +- **2026-03-08** — [Released "Dintal Claw" — a GenericAgent-powered government-affairs bot](https://mp.weixin.qq.com/s/eiEhwo-j6S-WpLxgBnNxBg). +- **2026-03-01** — [Featured by Jiqizhixin (机器之心)](https://mp.weixin.qq.com/s/uVWpTTF5I1yzAENV_qm7yg). +- **2026-01-16** — GenericAgent **V1.0** public release. -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 -- **L1 — Insight Index**: Minimal memory index for fast routing and recall -- **L2 — Global Facts**: Stable knowledge accumulated over long-term operation -- **L3 — Task Skills / SOPs**: Reusable workflows for completing specific task types -- **L4 — Session Archive**: Archived task records distilled from finished sessions for long-horizon recall - -2️⃣ **Autonomous Execution Loop** - -> _Perceive environment state → Task reasoning → Execute tools → Write experience to memory → Loop_ - -The entire core loop is just **~100 lines of code** (`agent_loop.py`). - -3️⃣ **Minimal Toolset** -> _GenericAgent provides only **9 atomic tools**, forming the foundational capabilities for interacting with the outside world._ - -| Tool | Function | -|------|------| -| `code_run` | Execute arbitrary code | -| `file_read` | Read files | -| `file_write` | Write files | -| `file_patch` | Patch / modify files | -| `web_scan` | Perceive web content | -| `web_execute_js` | Control browser behavior | -| `ask_user` | Human-in-the-loop confirmation | - -> Additionally, 2 **memory management tools** (`update_working_checkpoint`, `start_long_term_update`) allow the agent to persist context and accumulate experience across sessions. - -4️⃣ **Capability Extension Mechanism** -> _Capable of dynamically creating new tools._ - -Via `code_run`, GenericAgent can dynamically install Python packages, write new scripts, call external APIs, or control hardware at runtime — crystallizing temporary abilities into permanent tools. - -
- GenericAgent Workflow -
GenericAgent Workflow Diagram -
- - -## ⭐ Support +## ⭐ Community & Support If this project helped you, please consider leaving a **Star!** 🙏 -You're also welcome to join our **GenericAgent Community Group** for discussion, feedback, and co-building 👏 +You're also welcome to join the **GenericAgent Community Group** for discussion, feedback, and co-building 👏
- +
WeChat Group 18
WeChat Group 18 QR Code		WeChat Group 18
WeChat Group 18 QR
-## 🚩 Friendly Links +### 🚩 Friendly Links -Thanks for the support from the LinuxDo community! +Thanks to the **LinuxDo** community for the support! -[![LinuxDo](https://img.shields.io/badge/社区-LinuxDo-blue?style=for-the-badge)](https://linux.do/) +[![LinuxDo](https://img.shields.io/badge/Community-LinuxDo-blue?style=for-the-badge)](https://linux.do/) -**Community GUIs** (independent open-source projects): +**Community GUIs** *(independent open-source projects)*: - [chilishark27/ga-manager](https://github.com/chilishark27/ga-manager) - [wangjc683/galley](https://github.com/wangjc683/galley) +--- + ## 📄 License -MIT License — see [LICENSE](LICENSE) - -*Disclaimer: This project does not build or operate any commercial website. Apart from DintalClaw, no institution, organization, or individual is currently officially authorized to conduct commercial activities under the GenericAgent name.* +Distributed under the **MIT License**. See [`LICENSE`](LICENSE) for full text. +> *Disclaimer: This project does not build or operate any commercial website. Apart from DintalClaw, no institution, organization, or individual is currently officially authorized to conduct commercial activities under the GenericAgent name.* --- - + + + ## 🌟 项目简介 -**GenericAgent** 是一个极简、可自我进化的自主 Agent 框架。核心仅 **~3K 行代码**，通过 **9 个原子工具 + ~100 行 Agent Loop**，赋予任意 LLM 对本地计算机的系统级控制能力，覆盖浏览器、终端、文件系统、键鼠输入、屏幕视觉及移动设备。 +**GenericAgent** 是一个极简、可自我进化的自主 Agent 框架。核心仅 **~3K 行代码**，通过 **9 个原子工具 + ~100 行 Agent Loop**，赋予任意 LLM 对本地计算机的系统级控制能力，覆盖浏览器、终端、文件系统、键鼠输入、屏幕视觉及移动设备（ADB）。 -它的设计哲学是：**不预设技能，靠进化获得能力。** +> 设计哲学 —— **不预设技能，靠进化获得能力。** 每解决一个新任务，GenericAgent 就将执行路径自动固化为 Skill，供后续直接调用。使用时间越长，沉淀的技能越多，形成一棵完全属于你、从 3K 行种子代码生长出来的专属技能树。 -> **🤖 自举实证** — 本仓库的一切，从安装 Git、`git init` 到每一条 commit message，均由 GenericAgent 自主完成。作者全程未打开过一次终端。 +> 🤖 **自举实证** — 本仓库的一切，从安装 Git、`git init` 到每一条 commit message，均由 GenericAgent 自主完成。作者全程未打开过一次终端。 + +### 📑 目录 + +- [核心特性](#-核心特性) +- [实例展示](#-实例展示) +- [快速开始](#-快速开始) +- [使用方式](#-使用方式) +- [架构设计](#-架构设计) +- [自我进化机制](#-自我进化机制) +- [与同类产品对比](#-与同类产品对比) +- [评测](#-评测) +- [路线图与最新动态](#-路线图与最新动态) +- [社区与支持](#-社区与支持) +- [许可](#-许可) + +--- ## 📋 核心特性 -- **自我进化**: 每次任务自动沉淀 Skill，能力随使用持续增长，形成专属技能树 -- **极简架构**: ~3K 行核心代码，Agent Loop 约百行，无复杂依赖，部署零负担 -- **强执行力**: 注入真实浏览器（保留登录态），9 个原子工具直接接管系统 -- **高兼容性**: 支持 Claude / Gemini / Kimi / MiniMax 等主流模型，跨平台运行 -- **极致省 Token**: 上下文窗口不到 30K，是其他 Agent（200K–1M）的零头。分层记忆让关键信息始终在场——噪声更少，幻觉更低，成功率反而更高，而成本低一个数量级。 -## 🧬 自我进化机制 +| 特性 | 说明 | +| :--- | :--- | +| 🧬 **自我进化** | 每次任务自动沉淀 Skill，能力随使用持续增长，形成专属技能树 | +| 🪶 **极简架构** | ~3K 行核心代码，Agent Loop 约百行，无复杂依赖，部署零负担 | +| ⚡ **强执行力** | 注入真实浏览器（保留登录态），9 个原子工具直接接管系统 | +| 🔌 **高兼容性** | 支持 Claude / Gemini / Kimi / MiniMax 等主流模型，跨平台运行 | +| 💰 **极致省 Token** | 上下文窗口不到 30K，是其他 Agent（200K–1M）的零头；噪声更少、幻觉更低、成功率更高，成本低一个数量级 | -这是 GenericAgent 区别于其他 Agent 框架的根本所在。 +--- -``` -[遇到新任务]-->[自主摸索](安装依赖、编写脚本、调试验证)--> -[将执行路径固化为 Skill]-->[写入记忆层]-->[下次同类任务直接调用] -``` +## 🎯 实例展示 -| 你说的一句话 | Agent 第一次做了什么 | 之后每次 | -|---|---|---| -| *"监控股票并提醒我"* | 安装 mootdx → 构建选股流程 → 配置定时任务 → 保存 Skill | **一句话启动** | -| *"用 Gmail 发这个文件"* | 配置 OAuth → 编写发送脚本 → 保存 Skill | **直接可用** | - -用几周后，你的 Agent 实例将拥有一套任何人都没有的专属技能树，全部从 3K 行种子代码中生长而来。 - - - -#### 🎯 实例展示 - -| 🧋 外卖下单 | 📈 量化选股 | -|:---:|:---:| -| Order Tea | Stock Selection | -| *"Order me a milk tea"* — 自动导航外卖 App，选品并完成结账 | *"Find GEM stocks with EXPMA golden cross, turnover > 5%"* — 量化条件筛股 | -| 🌐 自主网页探索 | 💰 支出追踪 | 💬 批量消息 | -| Web Exploration | Alipay Expense | WeChat Batch | -| 自主浏览并定时汇总网页信息 | *"查找近 3 个月超 ¥2K 的支出"* — 通过 ADB 驱动支付宝 | 批量发送微信消息，完整驱动微信客户端 | - - - -## 📅 最新动态 - -- **2026-05-15:** 🖥️ 桌面 GUI 发布 —— 一键安装现在会自带可直接运行的桌面端（`frontends/GenericAgent.exe`），开发者也可用 `python launch.pyw` 启动。 -- **2026-05-14:** 🆕 **Conductor 子 Agent 编排** —— 派发、监督、自动清理并行子 Agent；与 `/btw` 旁路子 Agent 互补，提供一等公民级的任务委派原语。 -- **2026-05-12:** 🆕 **TUI v2 正式发布**（`frontends/tuiapp_v2.py`）—— 重做视觉风格的 Textual 前端，支持图片粘贴折叠、文件粘贴、块删除、Ctrl+C 复制、历史导航，以及 `/llm` / `/export` / `/continue` 选择器。 -- **2026-04-21:** 📄 [技术报告已发布至 arXiv](https://arxiv.org/abs/2604.17091) — *GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization* -- **2026-04-11:** 引入 **L4 会话归档记忆**，并接入 scheduler cron 调度 -- **2026-03-23:** 支持个人微信接入作为 Bot 前端 -- **2026-03-10:** [发布百万级 Skill 库](https://mp.weixin.qq.com/s/q2gQ7YvWoiAcwxzaiwpuiQ?scene=1&click_id=7) -- **2026-03-08:** [发布以 GenericAgent 为核心的"政务龙虾" Dintal Claw](https://mp.weixin.qq.com/s/eiEhwo-j6S-WpLxgBnNxBg) -- **2026-03-01:** [GenericAgent 被机器之心报道](https://mp.weixin.qq.com/s/uVWpTTF5I1yzAENV_qm7yg) -- **2026-01-16:** GenericAgent V1.0 公开版本发布 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
🧋 外卖下单📈 量化选股
外卖下单量化选股
"Order me a milk tea" — 自动导航外卖 App，选品并完成结账"Find GEM stocks with EXPMA golden cross, turnover > 5%" — 量化条件筛股
🌐 自主网页探索💰 支出追踪
网页探索支付宝支出
自主浏览并定时汇总网页信息"查找近 3 个月超 ¥2K 的支出" — 通过 ADB 驱动支付宝
💬 批量消息
微信批量
批量发送微信消息，完整驱动微信客户端
--- ## 🚀 快速开始 > ⚠️ **Python 版本：** 推荐使用 **Python 3.11 或 3.12**。**请不要使用 Python 3.14**，与 `pywebview` 及部分依赖不兼容。 - +> > 📖 详细安装指南：**[installation_zh.md（中文）](docs/installation_zh.md)** · **[installation.md (English)](docs/installation.md)** ### 给 LLM Agent 看的 @@ -381,7 +495,7 @@ curl -fsSL https://raw.githubusercontent.com/lsdefine/GenericAgent/refs/heads/ma ### 给人类用户看的 -#### 方法一：一键安装（推荐） +#### 方法一 — 一键安装 *（推荐）* 一键安装会自动准备独立 Python 环境、Git、项目文件和桌面端，不污染系统环境。 @@ -403,30 +517,30 @@ curl -fsSL http://fudankw.cn:9000/files/ga_install.sh | bash frontends/GenericAgent.exe ``` -#### 方法二：Python 安装（开发者） +#### 方法二 — Python 安装 *（开发者）* ```bash git clone https://github.com/lsdefine/GenericAgent.git cd GenericAgent uv venv -uv pip install -e ".[ui]" # 核心 + UI 依赖 -cp mykey_template.py mykey.py # 填入你的 LLM API Key +uv pip install -e ".[ui]" # 核心 + UI 依赖 +cp mykey_template.py mykey.py # 填入你的 LLM API Key python launch.pyw ``` -> GenericAgent 更推荐由 Agent 在使用中自举环境，而不是预先手动装完整依赖。 - -完整引导流程见 [GETTING_STARTED.md](docs/GETTING_STARTED.md)。 - -📖 新手使用指南（图文版）：[飞书文档](https://my.feishu.cn/wiki/CGrDw0T76iNFuskmwxdcWrpinPb) +> 💡 GenericAgent 更推荐由 **Agent 在使用中自举环境**，而不是预先手动装完整依赖。 +📖 完整引导流程见 [`docs/GETTING_STARTED.md`](docs/GETTING_STARTED.md) +📖 新手图文版：[飞书文档](https://my.feishu.cn/wiki/CGrDw0T76iNFuskmwxdcWrpinPb) 📘 完整入门教程（Datawhale 出品）：[Hello GenericAgent](https://datawhalechina.github.io/hello-generic-agent/) · [GitHub](https://github.com/datawhalechina/hello-generic-agent) --- -## 🖥️ 前端启动方式 +## 💻 使用方式 -### 桌面端 +### 前端启动 + +#### 桌面端 一键安装自带桌面端，双击： @@ -434,7 +548,7 @@ python launch.pyw frontends/GenericAgent.exe ``` -### 终端 UI +#### 终端 UI 基于 [Textual](https://github.com/Textualize/textual) 的轻量键盘驱动界面。支持多会话并发、实时流式输出，有终端就能跑。 @@ -442,47 +556,128 @@ frontends/GenericAgent.exe python frontends/tuiapp_v2.py ``` -> **Windows 上 TUI 显示异常的排查思路：** -> 1. `textual` 版本太旧，先 `pip install -U textual`； -> 2. PowerShell / cmd 自带终端对 Unicode 和键位的支持比较糟糕，**Windows 上推荐用 Git Bash**，体验明显更稳； -> 3. 仍然显示异常时，可以让 GA 自己修一遍，参考 Prompt： -> > *"我在 Windows 的 PowerShell / cmd / Git Bash 中使用 `frontends/tuiapp_v2.py` 体验非常差，出现了一堆不兼容问题。请参考 Claude Code 在 Windows 终端的最佳配置，把所有字体和显示不兼容的问题修一遍。"* +
+⚠️ Windows 上 TUI 显示异常的排查思路 -### Streamlit UI +1. `textual` 版本太旧，先 `pip install -U textual`； +2. PowerShell / cmd 自带终端对 Unicode 和键位的支持比较糟糕，**Windows 上推荐用 Git Bash**，体验明显更稳； +3. 仍然显示异常时，可以让 GA 自己修一遍，参考 Prompt： + > *"我在 Windows 的 PowerShell / cmd / Git Bash 中使用 `frontends/tuiapp_v2.py` 体验非常差，出现了一堆不兼容问题。请参考 Claude Code 在 Windows 终端的最佳配置，把所有字体和显示不兼容的问题修一遍。"* + +
+ +#### Streamlit UI ```bash python launch.pyw ``` ---- - -## 💬 Bot 接口（IM） +### Bot 接口（IM） GenericAgent 支持 Telegram、微信、QQ、飞书 / Lark、企业微信、钉钉等 IM 前端。 -常用启动方式： +| 平台 | 启动命令 | +| :--- | :--- | +| Telegram | `python frontends/tgapp.py` | +| 微信 | `python frontends/wechatapp.py` | +| QQ | `python frontends/qqapp.py` | +| 飞书 / Lark | `python frontends/fsapp.py` | +| 企业微信 | `python frontends/wecomapp.py` | +| 钉钉 | `python frontends/dingtalkapp.py` | -```bash -python frontends/tgapp.py # Telegram -python frontends/wechatapp.py # 微信 -python frontends/qqapp.py # QQ -python frontends/fsapp.py # 飞书 / Lark -python frontends/wecomapp.py # 企业微信 -python frontends/dingtalkapp.py # 钉钉 +> 详细配置直接问 GenericAgent。 + +### 通用聊天命令 + +| 命令 | 说明 | +| :--- | :--- | +| `/new` | 开启新对话并清空当前上下文 | +| `/continue` | 列出可恢复会话快照 | +| `/continue N` | 恢复第 `N` 个可恢复会话 | + +--- + +## 🧠 架构设计 + +GenericAgent 通过 **分层记忆 × 最小工具集 × 自主执行循环** 完成复杂任务，并在执行过程中持续积累经验。 + +### 1️⃣ 分层记忆系统 + +> *记忆在任务执行过程中持续沉淀，使 Agent 逐步形成稳定且高效的工作方式。* + +| 层级 | 名称 | 说明 | +| :---: | :--- | :--- | +| **L0** | 元规则（Meta Rules） | Agent 的基础行为规则和系统约束 | +| **L1** | 记忆索引（Insight Index） | 极简索引层，用于快速路由与召回 | +| **L2** | 全局事实（Global Facts） | 在长期运行过程中积累的稳定知识 | +| **L3** | 任务 Skills / SOPs | 完成特定任务类型的可复用流程 | +| **L4** | 会话归档（Session Archive） | 从已完成任务中提炼出的归档记录，用于长程召回 | + +### 2️⃣ 自主执行循环 + +> *感知环境状态 → 任务推理 → 调用工具执行 → 经验写入记忆 → 循环* + +整个核心循环仅 **约百行代码**（[`agent_loop.py`](agent_loop.py)）。 + +### 3️⃣ 最小工具集 + +> *GenericAgent 仅提供 **9 个原子工具**，构成与外部世界交互的基础能力。* + +| 工具 | 功能 | +| :--- | :--- | +| `code_run` | 执行任意代码（Python / PowerShell） | +| `file_read` | 读取文件 | +| `file_write` | 写入 / 创建 / 覆盖文件 | +| `file_patch` | 修改文件 | +| `web_scan` | 感知网页内容 | +| `web_execute_js` | 控制浏览器行为 | +| `ask_user` | 人机协作确认 | +| `update_working_checkpoint` | *（记忆）* 短期工作记事板 | +| `start_long_term_update` | *（记忆）* 提炼长期记忆 | + +### 4️⃣ 能力扩展机制 + +> *具备动态创建新工具的能力。* + +通过 `code_run`，GenericAgent 可在运行时动态安装 Python 包、编写新脚本、调用外部 API 或控制硬件，将临时能力固化为永久工具。 + +
+ GenericAgent 工作流程 +
GenericAgent 工作流程图 +
+ +--- + +## 🧬 自我进化机制 + +这是 GenericAgent 区别于其他 Agent 框架的根本所在。 + +```text +[遇到新任务] + │ + ▼ +[自主摸索] ─► 安装依赖 · 编写脚本 · 调试验证 + │ + ▼ +[执行路径固化为 Skill] ─► 写入记忆层 + │ + ▼ +[下次同类任务直接调用] ``` -详细配置直接问 GenericAgent。 +| 你说的一句话 | 第一次做了什么 | 之后每次 | +| :--- | :--- | :--- | +| *"监控股票并提醒我"* | 安装 `mootdx` → 构建选股流程 → 配置定时任务 → 保存 Skill | **一句话启动** | +| *"用 Gmail 发这个文件"* | 配置 OAuth → 编写发送脚本 → 保存 Skill | **直接可用** | -通用聊天命令： +用几周后，你的 Agent 实例将拥有一套任何人都没有的专属技能树，全部从 3K 行种子代码中生长而来。 -- `/new` - 开启新对话并清空当前上下文 -- `/continue` - 列出可恢复会话快照 -- `/continue N` - 恢复第 `N` 个可恢复会话 +--- ## 📊 与同类产品对比 -| 特性 | GenericAgent | OpenClaw | Claude Code | -|------|:---:|:---:|:---:| +| 特性 | **GenericAgent** | OpenClaw | Claude Code | +| :--- | :---: | :---: | :---: | | **代码量** | ~3K 行 | ~530,000 行 | 已开源（体量大） | | **部署方式** | `pip install` + API Key | 多服务编排 | CLI + 订阅 | | **浏览器控制** | 注入真实浏览器（保留登录态） | 沙箱 / 无头浏览器 | 通过 MCP 插件 | @@ -490,18 +685,21 @@ python frontends/dingtalkapp.py # 钉钉 | **自我进化** | 自主生长 Skill 和工具 | 插件生态 | 会话间无状态 | | **出厂配置** | 几个核心文件 + 少量初始 Skills | 数百模块 | 丰富 CLI 工具集 | +--- -## 📈 评测 — 五大维度 +## 📈 评测 -> 📂 完整的评测数据集以及评测结果见： +> 📂 完整的评测数据集以及评测结果见：[**JinyiHan99/GA-Technical-Report**](https://github.com/JinyiHan99/GA-Technical-Report/tree/main) -| 维度 | 核心问题 | 使用的基准 | -|---|---|---| -| **1. 任务完成度与 Token 效率** | GA 能否以更低成本完成高难度任务？ | SOP-Bench、Lifelong AgentBench、RealFin-Benchmark | -| **2. 工具使用效率** | 最小原子工具集能否以更低开销替代专用工具集？ | Tool Efficiency Benchmark | -| **3. 记忆系统有效性** | 精简分层记忆能否超越冗余记忆和基于 Embedding 的检索器？ | SOP-Bench、LoCoMo、20-skill 压力测试 | -| **4. 自我进化能力** | Agent 能否在无人干预下将经验提炼为可复用的 SOP 与代码？ | 9 轮 LangChain 纵向研究、8 任务跨任务 Web 基准 | -| **5. 网页浏览能力** | 信息密度驱动设计能否适应开放网页？ | WebCanvas、BrowseComp-ZH、自定义任务 | +我们从 **五大维度** 评测 GenericAgent： + +| # | 维度 | 核心问题 | 使用的基准 | +| :---: | :--- | :--- | :--- | +| 1 | **任务完成度与 Token 效率** | GA 能否以更低成本完成高难度任务？ | SOP-Bench、Lifelong AgentBench、RealFin-Benchmark | +| 2 | **工具使用效率** | 最小原子工具集能否以更低开销替代专用工具集？ | Tool Efficiency Benchmark | +| 3 | **记忆系统有效性** | 精简分层记忆能否超越冗余记忆和基于 Embedding 的检索器？ | SOP-Bench、LoCoMo、20-skill 压力测试 | +| 4 | **自我进化能力** | Agent 能否在无人干预下将经验提炼为可复用的 SOP 与代码？ | 9 轮 LangChain 纵向研究、8 任务跨任务 Web 基准 | +| 5 | **网页浏览能力** | 信息密度驱动设计能否适应开放网页？ | WebCanvas、BrowseComp-ZH、自定义任务 | 以上维度的基线包括 **Claude Code**、**OpenAI CodeX** 和 **OpenClaw**，分别在 *Claude Sonnet 4.6*、*Claude Opus 4.6*、*GPT-5.4* 和 *MiniMax M2.7* 底座上进行评测。 @@ -518,87 +716,69 @@ python frontends/dingtalkapp.py # 钉钉 +--- -## 🧠 工作机制 +## 📅 路线图与最新动态 -GenericAgent 通过**分层记忆 × 最小工具集 × 自主执行循环**完成复杂任务，并在执行过程中持续积累经验。 +- **2026-05-15** — 🖥️ **桌面 GUI 发布**。一键安装会自带可直接运行的桌面端（`frontends/GenericAgent.exe`），开发者也可用 `python launch.pyw` 启动。 +- **2026-05-14** — 🆕 **Conductor 子 Agent 编排**。派发、监督、自动清理并行子 Agent；与 `/btw` 旁路子 Agent 互补，提供一等公民级的任务委派原语。 +- **2026-05-12** — 🆕 **TUI v2 正式发布**（`frontends/tuiapp_v2.py`）。重做视觉风格的 Textual 前端，支持图片粘贴折叠、文件粘贴、块删除、Ctrl+C 复制、历史导航，以及 `/llm` / `/export` / `/continue` 选择器。 +- **2026-04-21** — 📄 [**技术报告已发布至 arXiv**](https://arxiv.org/abs/2604.17091) — *GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization*。 +- **2026-04-11** — 引入 **L4 会话归档记忆**，并接入 scheduler cron 调度。 +- **2026-03-23** — 支持个人微信接入作为 Bot 前端。 +- **2026-03-10** — [发布百万级 Skill 库](https://mp.weixin.qq.com/s/q2gQ7YvWoiAcwxzaiwpuiQ?scene=1&click_id=7)。 +- **2026-03-08** — [发布以 GenericAgent 为核心的"政务龙虾" Dintal Claw](https://mp.weixin.qq.com/s/eiEhwo-j6S-WpLxgBnNxBg)。 +- **2026-03-01** — [被机器之心报道](https://mp.weixin.qq.com/s/uVWpTTF5I1yzAENV_qm7yg)。 +- **2026-01-16** — GenericAgent **V1.0** 公开版本发布。 -1️⃣ **分层记忆系统** -> 记忆在任务执行过程中持续沉淀，使 Agent 逐步形成稳定且高效的工作方式 +--- +## ⭐ 社区与支持 -- **L0 — 元规则（Meta Rules）**：Agent 的基础行为规则和系统约束 -- **L1 — 记忆索引（Insight Index）**：极简索引层，用于快速路由与召回 -- **L2 — 全局事实（Global Facts）**：在长期运行过程中积累的稳定知识 -- **L3 — 任务 Skills / SOPs**：完成特定任务类型的可复用流程 -- **L4 — 会话归档（Session Archive）**：从已完成任务中提炼出的归档记录，用于长程召回 +如果这个项目对你有帮助，欢迎点一个 **Star!** 🙏 -2️⃣ **自主执行循环** +也欢迎加入 **GenericAgent 体验交流群**，一起交流、反馈、共建 👏 -> 感知环境状态 → 任务推理 → 调用工具执行 → 经验写入记忆 → 循环 - -整个核心循环仅 **约百行代码**（`agent_loop.py`）。 - -3️⃣ **最小工具集** ->GenericAgent 仅提供 **9 个原子工具**，构成与外部世界交互的基础能力 - -| 工具 | 功能 | -|------|------| -| `code_run` | 执行任意代码 | -| `file_read` | 读取文件 | -| `file_write` | 写入文件 | -| `file_patch` | 修改文件 | -| `web_scan` | 感知网页内容 | -| `web_execute_js` | 控制浏览器行为 | -| `ask_user` | 人机协作确认 | - -> 此外，还有 2 个**记忆管理工具**（`update_working_checkpoint`、`start_long_term_update`），使 Agent 能够跨会话积累经验、维持持久上下文。 - -4️⃣ **能力扩展机制** -> 具备动态创建新的工具能力 -> -通过 `code_run`，GenericAgent 可在运行时动态安装 Python 包、编写新脚本、调用外部 API 或控制硬件，将临时能力固化为永久工具。 - -
- GenericAgent 工作流程 -
GenericAgent 工作流程图 -
- -## ⭐ 支持 -如果这个项目对您有帮助，欢迎点一个 **Star!** 🙏 - -同时也欢迎加入我们的**GenericAgent体验交流群**，一起交流、反馈和共建 👏
- +
微信群 18
微信群 18 二维码		微信群 18
微信群 18 二维码
-## 🚩 友情链接 +### 🚩 友情链接 感谢 **LinuxDo** 社区的支持！ [![LinuxDo](https://img.shields.io/badge/社区-LinuxDo-blue?style=for-the-badge)](https://linux.do/) -**社区 GUI 客户端**（独立开源项目）： +**社区 GUI 客户端** *（独立开源项目）*： - [chilishark27/ga-manager](https://github.com/chilishark27/ga-manager) - [wangjc683/galley](https://github.com/wangjc683/galley) +--- ## 📄 许可 -MIT License — 详见 [LICENSE](LICENSE) -*声明：本项目未构建任何商业站点；除 DintalClaw 外，目前未官方授权任何机构、组织或个人以 GenericAgent 名义从事商业活动。* +基于 **MIT License** 发布，详见 [`LICENSE`](LICENSE)。 + +> *声明：本项目未构建任何商业站点；除 DintalClaw 外，目前未官方授权任何机构、组织或个人以 GenericAgent 名义从事商业活动。* + +--- ## 📈 Star History +
+ - - - - Star History Chart - + + + + Star History Chart + + +

+