Instrukt
Integrated AI environment in the terminal. Build, test and instruct agents.
freememory-knowledge
329
Stars
+8
Stars/month
0
Releases (6m)
Star Growth
+1 (0.3%)
Overview
Instrukt是一个基于终端的AI集成环境，专为高级用户设计。它允许创建和管理模块化AI代理，这些代理以Python包的形式存在，可以扩展、共享并附加工具。该工具的核心特色是在Docker容器中运行代理，确保安全的沙盒执行环境。用户可以通过自然语言指令控制代理，并为代理配备文档索引进行问答增强生成（RAG）。系统内置编程助手和聊天Q&A代理，支持为任何代码库创建索引以提供上下文感知的编程帮助。基于Langchain、Textual和Chroma构建，提供丰富的终端界面体验，支持markdown和代码高亮显示。虽然仍在开发中，但已具备完整的代理创建、工具集成和文档问答功能。
Deep Analysis
Key Differentiator
vs LangChain CLI / Open Interpreter: terminal-native TUI with Docker sandboxing, modular agent packages, and language-aware code indexing — designed for headless servers and SSH workflows
⚡ Capabilities
- • Terminal-based AI agent creation and instruction environment
- • Document indexing with RAG for Q&A workflows
- • Code indexing with language detection and retrieval
- • Modular agent system with drop-in Python packages
- • Docker container sandboxing for secure execution
- • Keyboard-driven TUI with Rich/Textual interface
🔗 Integrations
LangChainOpenAIChromaDockerTextualRich
✓ Best For
- ✓ Terminal-native code analysis and documentation Q&A via RAG
- ✓ Developers wanting secure sandboxed AI agent execution
- ✓ SSH/headless server environments needing AI tooling
✗ Not Ideal For
- ✗ Non-technical users (keyboard-centric TUI design)
- ✗ Teams needing multi-LLM provider flexibility today
- ✗ Web-based or mobile AI applications
Languages
Python
Deployment
pip installDocker (CUDA support)headless serversSSHterminal multiplexers
⚠ Known Limitations
- ⚠ Only OpenAI supported as LLM provider currently
- ⚠ Work-in-progress with expected bugs
- ⚠ Windows support limited to WSL2 only
- ⚠ No local LLM integration yet (roadmapped)
- ⚠ Requires g++ and libmagic for bare container builds
Pros
- + 模块化架构使代理可以作为独立Python包扩展和共享
- + Docker沙盒执行环境确保安全性
- + 丰富的终端界面支持键盘操作和彩色输出
Cons
- - 项目仍在开发中，存在bug和API变更
- - 需要Docker环境进行沙盒执行
- - 仅支持终端界面，对非技术用户不够友好
Use Cases
- • 为代码库创建RAG索引的编程助手
- • 基于自定义文档的问答系统
- • 构建带工具的自定义AI代理
Getting Started
1. 运行 pip install instrukt[all] 安装工具
2. 设置 OPENAI_API_KEY 环境变量
3. 执行 instrukt 命令启动终端界面