codel
✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.
freeagent-frameworks
2.4k
Stars
+0
Stars/month
0
Releases (6m)
Star Growth
Overview
codel是一个完全自主的AI代理工具，能够在安全的Docker沙盒环境中执行复杂的开发任务和项目。该工具集成了终端、浏览器和代码编辑器功能，可以自动检测并执行下一步操作，无需人工干预。codel具备内置浏览器，能够实时获取最新的在线信息如教程和文档，同时提供内置文本编辑器供用户在浏览器中查看所有修改的文件。所有执行的命令和输出都会保存在PostgreSQL数据库中，便于追踪和回顾。该工具支持根据用户任务自动选择合适的Docker镜像，提供现代化的Web界面。codel支持多种语言模型，包括OpenAI的GPT系列和本地部署的Ollama模型，采用自托管方式部署，让用户完全控制数据和执行环境。
Deep Analysis
Key Differentiator
vs Open Interpreter / ChatDev: automatic Docker image selection per task + integrated browser + editor in one autonomous agent — fully sandboxed execution with local LLM support via Ollama
⚡ Capabilities
- • Fully autonomous AI agent with terminal, browser, and editor capabilities
- • Sandboxed Docker execution environment for security
- • Automatic next-step detection without human prompting
- • Built-in web browser for information fetching
- • PostgreSQL-backed command history and persistence
- • Automatic Docker image selection based on user task
🔗 Integrations
OpenAI GPT-4Ollama (local LLMs)DockerPostgreSQLgo-rod (browser)
✓ Best For
- ✓ Autonomous development tasks in sandboxed environments
- ✓ Complex multi-step project automation
- ✓ Web research integrated with code editing workflows
✗ Not Ideal For
- ✗ Tasks requiring human approval at every step
- ✗ Lightweight single-command operations
- ✗ Environments where Docker is not available
Languages
Go
Deployment
Docker containers (GitHub Container Registry)web UI at localhost:3000
⚠ Known Limitations
- ⚠ Requires API keys for external models
- ⚠ Ollama needs separate installation
- ⚠ Task complexity depends on model capabilities
- ⚠ Docker infrastructure required
Pros
- + 在Docker沙盒环境中运行，确保系统安全性和隔离性
- + 完全自主操作，能自动检测任务步骤并执行，减少人工干预
- + 集成浏览器、编辑器和终端，提供完整的开发环境体验
Cons
- - 需要Docker环境和PostgreSQL数据库，部署配置相对复杂
- - 依赖外部API密钥（如OpenAI），可能产生使用成本
- - 作为自主AI代理，在复杂任务中可能存在不可预测的行为
Use Cases
- • 自动化软件开发项目，从需求分析到代码实现
- • 复杂系统配置和部署任务的自动执行
- • 需要浏览器研究、代码编写和终端操作协同的开发工作流
Getting Started
首先安装Docker并从GitHub Container Registry拉取codel镜像；然后配置环境变量文件，设置OpenAI API密钥或Ollama模型配置；最后运行Docker容器映射端口3000，访问localhost:3000开始使用