gptme Agent工作流 是 AI Skill Hub 本期精选AI工具之一。已获得 4.3k 颗 GitHub Star,综合评分 8.2 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
gptme Agent工作流 是一款基于 Python 开发的开源工具,专注于 AI代理、工作流自动化、终端工具 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
gptme Agent工作流 是一款基于 Python 开发的开源工具,专注于 AI代理、工作流自动化、终端工具 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:pip 安装(推荐)
pip install gptme
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install gptme
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/gptme/gptme
cd gptme
pip install -e .
# 验证安装
python -c "import gptme; print('安装成功')"
# 命令行使用
gptme --help
# 基本用法
gptme input_file -o output_file
# Python 代码中调用
import gptme
# 示例
result = gptme.process("input")
print(result)
# gptme 配置文件示例(config.yml) app: name: "gptme" debug: false log_level: "INFO" # 运行时指定配置文件 gptme --config config.yml # 或通过环境变量配置 export GPTME_API_KEY="your-key" export GPTME_OUTPUT_DIR="./output"
<p align="center"> <img src="https://gptme.org/media/logo.png" width=150 /> </p>
<p align="center"> <i>/ʤiː piː tiː miː/</i> <br> <sub><a href="https://gptme.org/docs/misc/acronyms.html">what does it stand for?</a></sub> </p>
<p align="center"> <a href="https://gptme.org/docs/getting-started.html">Getting Started</a> • <a href="https://gptme.org/downloads/">Downloads</a> • <a href="https://gptme.org/">Website</a> • <a href="https://gptme.org/docs/">Documentation</a> </p>
<p align="center"> <a href="https://github.com/gptme/gptme/actions/workflows/build.yml"> <img src="https://github.com/gptme/gptme/actions/workflows/build.yml/badge.svg" alt="Build Status" /> </a> <a href="https://github.com/gptme/gptme/actions/workflows/docs.yml"> <img src="https://github.com/gptme/gptme/actions/workflows/docs.yml/badge.svg" alt="Docs Build Status" /> </a> <a href="https://codecov.io/gh/gptme/gptme"> <img src="https://codecov.io/gh/gptme/gptme/graph/badge.svg?token=DYAYJ8EF41" alt="Codecov" /> </a> <br> <a href="https://pypi.org/project/gptme/"> <img src="https://img.shields.io/pypi/v/gptme" alt="PyPI version" /> </a> <a href="https://pepy.tech/project/gptme"> <img src="https://img.shields.io/pepy/dt/gptme" alt="PyPI - Downloads all-time" /> </a> <a href="https://pypistats.org/packages/gptme"> <img src="https://img.shields.io/pypi/dd/gptme?color=success" alt="PyPI - Downloads per day" /> </a> <a href="https://doi.org/10.5281/zenodo.22816651"> <img src="https://zenodo.org/badge/DOI/10.5281/zenodo.22816651.svg" alt="DOI" /> </a> <br> <a href="https://discord.gg/NMaCmmkxWv"> <img src="https://img.shields.io/discord/1271539422017618012?logo=discord&style=social" alt="Discord" /> </a> <a href="https://x.com/gptmeorg"> <img src="https://img.shields.io/twitter/follow/gptmeorg?style=social" alt="X.com" /> </a> <br> <a href="https://gptme.org/docs/projects.html"> <img src="https://gptme.org/badge.svg" alt="Built with gptme" /> </a> </p>
<p align="center"> 📜 A personal AI agent that runs <i>anywhere a terminal runs</i> — your laptop, ssh sessions, tmux, headless servers, CI pipelines.<br/> Provider-agnostic, local-first, and unconstrained: ships with shell, Python, web, vision, and everything else an agent needs.<br/> A great coding agent, but general-purpose enough to assist in all kinds of knowledge-work. </p>
<p align="center"> Free and open-source. Works with Anthropic, OpenAI, Google, SpaceXAI, DeepSeek, OpenRouter, Requesty, your existing ChatGPT/SuperGrok subscription, or fully local via Ollama and any OpenAI-compatible server — your data, your models, your terminal.<br/> A capable <a href="https://gptme.org/docs/alternatives.html">alternative</a> to Claude Code, Codex, and Grok Bot, and a development-focused peer to self-hosted agents like OpenClaw and Hermes Agent — one of the first agent CLIs (Spring 2023), still in very active development. </p>
gptme-util memory CLI — save, recall, search, supersede, and audit entries from any terminal.llama.cpp.gptme-server and hosted at chat.gptme.org.GPTME_TOOL_SOUNDS=true.- Python 3.10 or newer - Credentials for at least one LLM provider: - Fastest no-credit-card path: start gptme, choose OpenRouter in the startup provider setup (browser OAuth), then run gptme "hello" -m openrouter/openrouter/free. On an existing setup, use /account setup openrouter inside a session. See [Getting Started][docs-getting-started]. - Subscriptions work too: sign in with your ChatGPT Plus/Pro or SuperGrok plan via gptme-auth openai-subscription or gptme-auth grok-subscription, no API key needed (see [providers docs][docs-providers]). - You can also set API keys manually for Anthropic (ANTHROPIC_API_KEY), OpenAI (OPENAI_API_KEY), OpenRouter (OPENROUTER_API_KEY), and other providers. - Local models need no key at all — run Ollama (or any OpenAI-compatible server) and use -m local/<model>, see [providers docs][docs-providers].
pipx install gptme
gptme service init --name Ada --model anthropic/claude-haiku-4-5 --work-dir ~/ada
systemctl --user daemon-reload systemctl --user enable --now Ada.timer
For full setup instructions, see the [Getting Started guide][docs-getting-started].
```sh
curl -sSf https://gptme.ai/install.sh | sh # auto-detects uv or pipx
Or install directly with pipx install gptme / uv tool install gptme (Python 3.10+). See Installation above, the [Getting Started guide][docs-getting-started], and [System dependencies][docs-system-dependencies] for the extras individual tools need.
gptme
You'll be greeted with a prompt. Type your request and gptme will respond, using tools as needed.
```sh
gptme # start an interactive chat
gptme 'fix the failing tests' # start with a prompt
gptme 'review this' main.py README.md # include files (or URLs, or a GitHub PR) as context
gptme -m anthropic/claude-sonnet-4-6 # pick a model for this session
gptme -t read-only 'summarize the repo' # restrict which tools are available
gptme -y 'run the tests and fix them' # auto-approve tool calls, stay in the loop
gptme -n 'summarize the git diff' # fully non-interactive, for scripts and CI
gptme -r # resume the most recent conversation
During a conversation, /help lists the slash-commands — /undo, /backtrack, /tools, /tokens, /compact, /model, and more. gptme --help shows every flag, and gptme <subcommand> reaches the other CLIs (gptme tools list, gptme chats search, gptme skills list).
Full reference: CLI docs · [commands][docs-commands] · usage guide · [automation][docs-automation]
| Terminal UI | Web UI | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
[ <details> <summary>Features</summary> <ul> <li> Textual-based <code>gptme-tui</code> (<code>pipx install 'gptme[tui]'</code>) <li> Queue prompts while the agent is working <li> Collapsible tool output <li> Status bar with model, token usage, and agent state <li> Or use the plain <code>gptme</code> CLI for scripted and non-interactive use </ul> </details> </td> <td width="50%"> <details> <summary>Features</summary> <ul> <li> Chat with gptme from your browser <li> Access to all tools and features <li> Modern, responsive interface <li> Self-hostable <li> Available at <a href="https://chat.gptme.org">chat.gptme.org</a> </ul> </details> </td> </tr> <tr> <th>Fibonacci</th> <th>Mandelbrot with curses</th> </tr> <tr> <td width="50%"> <details> <summary>Steps</summary> <ol> <li> Create a new dir 'gptme-test-fib' and git init <li> Write a fib function to fib.py, commit <li> Create a public repo and push to GitHub </ol> </details> </td> <td width="50%"> <details> <summary>Steps</summary> <ol> <li> Render mandelbrot with curses to mandelbrot_curses.py <li> Program runs <li> Add color </ol> </details> </td> </tr> </table> [!NOTE] The terminal recordings above are from 2023 and show the classic CLI. More recordings are kept in the [Demo archive][docs-demos], and more up-to-date walkthroughs are in the [Examples][docs-examples]. With optional extraspipx install 'gptme[browser]' # Playwright for web browsing pipx install 'gptme[all]' # Everything Get configuration suggestionsgptme 'suggest improvements to my vimrc' ⚙️ ConfigurationCreate ```toml [user] name = "User" about = "I am a curious human programmer." response_preference = "Don't explain basic concepts" [prompt] How do I configure it?Configuration lives in Do I need an API key?No — you can also use a subscription you already pay for, or run a local model: - Subscription: If setup is missing or broken, run 🔌 Extensibility: Plugins, Skills & Lessonsgptme has a layered extensibility system that lets you tailor it to your workflow: [Plugins][docs-plugins] — extend gptme with custom tools, hooks, and commands via Python packages: ```toml 🔗 Integrations: MCP & ACP[MCP (Model Context Protocol)][docs-mcp] — gptme works in both directions: - MCP client: discover and load external MCP servers as gptme tools. - MCP server: expose gptme's persistent shell, Python REPL, and file tools to Claude Desktop, Cursor, or any other MCP client. ```sh pipx install gptme # MCP support included by default How does gptme compare to other AI coding assistants?gptme is open source and model-agnostic, runs in any terminal, and is built for persistent autonomous agents whose memory lives in a git repo you own — not just interactive pair programming. It's compared two ways: against coding agents (Claude Code, Codex, Cursor, Cline, Aider, OpenHands) and against persistent personal agents (OpenClaw, Hermes Agent, Grok Bot, Devin). See [Alternatives][docs-alternatives] for the maintained tables. ❓ FAQShort answers with pointers into the [documentation][docs] — the docs are the source of truth, this section just gets you to the right page.
🇨🇳 中文文档镜像
AI 翻译
2026-05-25
英文原文章节由系统翻译为中文摘要,便于快速理解。完整原文见上方 "📑 README 深度解析"。
📌 简介
gptme 是一个强大的 AI 终端助手,旨在通过自然语言交互提升开发效率。它不仅是一个聊天界面,更是一个能够理解并操作本地环境的智能代理,帮助开发者在命令行中更高效地完成任务。 ⚡ 功能介绍
gptme 具备卓越的自动化能力:支持通过 shell 和 python 工具在本地执行代码;能够利用 patch 工具对文件进行增量读写与修改;集成 Playwright 实现网页搜索与浏览;并具��� Vision 能力,能够理解并处理图像信息。 📋 环境依赖
运行 gptme 需要 Python 3.10 或更高版本。此外,您需要配置至少一个 LLM 提供商的凭据,支持通过 OpenRouter 进行交互式 OAuth 配置,或手动设置 Anthropic 等平台的 API keys。 🛠 安装步骤(Docker/pip/源码)
推荐使用 pipx 进行安装(需 Python 3.10+),执行 `pipx install gptme` 即可快速部署。如果需要增强功能,可以使用 `pipx install 'gptme[browser]'` 安装浏览器支持,或使用 `pipx install 'gptme[all]'` 获取完整功能集。 🚀 使用教程
安装完成后,直接在终端输入 `gptme` 即可启动。您可以像聊天一样输入自然语言请求,gptme 会根据需求自动调用相应的工具来执行任务。它适用于代码开发、Shell 命令辅助、数据分析以及通过交互式学习探索新技术的多种场景。 ⚙️ 配置说明(含 MCP / env)
用户可以通过创建 `~/.config/gptme/config.toml` 文件来自定义个人信息、回复偏好及 Prompt 模板。此外,可以通过设置环境变量(如 `export ANTHROPIC_API_KEY=your-key`)来管理 API 密钥。您还可以利用 gptme 的建议功能来优化配置文件。 🔌 API 说明
gptme 通过环境变量管理各类 LLM 的 API keys,确保安全且灵活地调用 Anthropic 等模型服务。开发者可以根据需求配置不同的 API 访问权限,以驱动其核心的智能代理功能。 🔄 工作流/模块
gptme 拥有强大的分层扩展系统。通过 Plugins,您可以利用 Python 包扩展自定义工具和命令;通过内置的 MCP (Model Context Protocol) 支持,gptme 可以动态发现并加载 MCP 服务器,从而将数据库、API 和文件系统等外部工具无缝集成到工作流中。 ❓ FAQ 摘要
本章节包含了关于 gptme 使用过程中常见问题的解答,涵盖了从安装、配置到功能使用的疑难点,帮助开发者快速解决在使用过程中遇到的各类技术问题。
🎯 aiskill88 AI 点评
A 级
2026-05-21
设计思路新颖,将AI代理与本地工具有机结合。代码质量高,社区活跃,是构建智能工作流的优秀框架。 📚 实用指南(长尾问题)
适合谁
最佳实践
常见错误
部署方案
⚡ 核心功能
👥 适合谁
⭐ 最佳实践
⚠️ 常见错误
👥 适合人群🎯 使用场景
⚖️ 优点与不足✅ 优点
⚠️ 不足
⚠️ 使用须知
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。 建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。 📄 License 说明
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。 🔗 相关工具推荐📚 相关教程推荐 📰 相关 AI 新闻
🍿 AI 圈相关吃瓜
🧩 你可能还需要
基于当前 Skill 的能力图谱,自动补全的工具组合
❓ 常见问题 FAQ主要支持Anthropic Claude系列模型,可扩展配置其他模型
💡 AI Skill Hub 点评
经综合评估,gptme Agent工作流 在AI工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。 🌐 原始信息
🔗 原始来源
🐙 GitHub 仓库 https://github.com/gptme/gptme
🌐 官方网站 https://gptme.org/docs/
收录时间:2026-05-14 · 更新时间:2026-05-16 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。 |