概览
主要功能
- 执行shell和Python命令
- 在工作目录支持读写文件
- 支持网页浏览和页面获取
- 具有视觉支持功能，对图像输入起作用
- 可以切换多种模型后端（OpenAI、 Anthropic、局域网）
- 持久存储会话历史记录为文本文件
价格
- 模型
- Free
- 评分
- 4.5 / 5 (6)
使用场景
从终端中自动化编码任务
使用gptme来读取、编辑和重构工作目录中的文件，同时运行shell或Python命令，将整个开发循环都进行在终端中。
使用局域网模型运行私有代理
将gptme与Ollama或其他本地后台结合来获得一个手动操作的助手，它执行命令编辑代码而不需要发送数据到公共网络的服务商中。
编写可重复的智能工作流程
将gptme嵌入到现有shell脚本和管道中，可以自动化网页获取、文件处理或图像分析，会话历史记录以可编辑的文本文件的形式保存下来。
开发会话的恢复和分享
如果会话历史记录以可编辑的文本文件保存，则用户可以暂停长期开发session，调整上下文或将此会话历史记录与同事共享
优点 & 缺点
优点
- 完全在终端中运行，需要极少的配置
- 支持多家的服务供应商，包括本地供应商
- 透明的工具使用可以被检查和控制
- 开源，可嵌入到您的现有工作流程中
缺点
- 命令行UI需要一定的学习成本
- 功能取决于您选择的模型
- UI不如商业版AI开发人员助手那么完善
评测
6 个评分的平均值。
登录以留下评测。
Compared a few options
Evaluated this against two competitors. Where it wins: file reading and editing in the working directory and supports multiple model providers, including local ones. Where it lags: command-line interface has a learning curve. On balance the feature set — especially shell and Python command execution — justifies the 4 stars for our use case.
Does the job
Pretty happy overall. File reading and editing in the working directory just works and runs entirely in the terminal with minimal setup. Command-line interface has a learning curve can be annoying, but no dealbreakers — I'd recommend it to a friend without hesitating.
Use it every day
Honestly didn't expect to like it this much. Vision support for image inputs is exactly what I needed, and transparent tool use you can inspect and control. but I reach for it almost every day now and it just clicks.
Skeptical, then convinced
I went in skeptical — most tools in this space overpromise. It actually delivers on pluggable model backends (OpenAI, Anthropic, local), and transparent tool use you can inspect and control caught me off guard. still, I'd recommend giving it a real trial.
Years in this space
I've evaluated a lot of these over the years. What stands out here is persistent, file-based conversation history — handled better than most — and runs entirely in the terminal with minimal setup. Worth the time if this is your use case.
Years in this space
I've evaluated a lot of these over the years. What stands out here is persistent, file-based conversation history — handled better than most — and transparent tool use you can inspect and control. Command-line interface has a learning curve is my one real gripe. Worth the time if this is your use case.
问答
What are the use cases?
gptme is general-purpose but excels at: Coding: Write, refactor, debug code Research: Web browsing, data collection Automation: File management, CI tasks Documentation: Generate docs, summaries Testing: Write tests, run tests, fix failures DevOps: Server management, deployment
Asked by Mohammed Al-Amin · May 26, 2026
How do I use gptme in CI/CD?
gptme runs in CI pipelines: # GitHub Actions - name: Run gptme run: | pip install gptme gptme --non-interactive "Review PR and suggest improvements"
Asked by Qiu Yan · May 21, 2026
What is the plugin system?
gptme has a full plugin system: Skills: Custom tools and capabilities Hooks: Pre/post execution hooks Integrations: External service connectors Community plugins: gptme-contrib repository Example plugins: Twitter/X bot Discord bot Email tools Consortium (multi-agent)
Asked by Hana Kobayashi · May 11, 2026
How do I create autonomous agents?
Use gptme-agent-template for persistent autonomous agents: Clone template: git clone https://github.com/gptme/gptme-agent-template Configure agent: # config.yaml name: "MyAgent" role: "Code reviewer" schedule: "hourly" Run: python agent.py See Bob for an example autonomous agent that has been running continuously since late 2024.
Asked by Olga Ivanova · May 6, 2026
What is the Lessons system?
The Lessons system provides contextual guidance and best practices that are automatically included when relevant: Project-specific lessons: Custom guidance for your project Best practices: Coding patterns and conventions Context injection: Automatic context based on situation
Asked by Ola Eriksen · Apr 30, 2026
提问
本当常用服务的形嵻箥别 的替代品
smolagents本当常用服务的形嵻箥别使用 Hugging Face 的轻量级 Python 库创建几行代码的 AI 代理
Mini LLM Flow本当常用服务的形嵻箥别最小化的 100 行 LLM 框架，用于构建自我编程代理工作流程
upsonicAI本当常用服务的形嵻箥别开源的代理框架，用于创建任务特定数字工人和垂直AI代理
AI-Powered RAG Workflow for n8n本当常用服务的形嵻箥别使用 n8n，以 Google Drive 文件为基础回答您的问题
ControlFlow本当常用服务的形嵻箥别用于构建具有任务中心设计的自主AI工作流的Python框架。
开源，一键复制代码片段，快速构建AI智能体
roboneo art本当常用服务的形嵻箥别AI绘画生成器，秒级从文本提示转换为优质图像。
Remove Watermark本当常用服务的形嵻箥别免費 AI 工具，立即從圖片中移除水印和Logo
