Mini Kode AI Agent

Mini-Kode

An educational AI coding assistant project that helps you understand and hack modern AI coding assistant systems.

🌟 Why Mini-Kode?

Mini-Kode is an educational project designed to help developers understand modern Coding Agent architecture. We strike the perfect balance between overly complex open-source projects and simplistic demo examples, offering a complete yet manageable implementation (14K lines of production code) with:

• 📚 Education-First Design - Clean architecture built on OpenAI SDK with thoughtful type design and comprehensive comments
• 🛠️ Complete Tool System - Unified interface with comprehensive tools for file operations, search, and command execution
• 🔌 MCP Integration - Connect to external MCP servers for extended functionality
• ⚙️ Multi-LLM Support - Compatible with OpenAI APIs, including GLM, DeepSeek, MiniMax, and other mainstream models
• 🤖 Agent Loop - Complete LLM workflow with streaming responses and human-in-the-loop permission approval
• 🎨 Modern UI - React/Ink-based terminal interface with theme support

🚀 Quick Start (Install & Use)

Install Globally

npm install -g mini-kode

Set Up API Key

DeepSeek (tested and verified):

export DEEPSEEK_API_KEY="your-deepseek-api-key"

Or use GLM (智谱AI) (tested and verified):

export GLM_API_KEY="your-glm-api-key"

Or use MiniMax:

export MINIMAX_API_KEY="your-minimax-api-key"
# Optional: target mainland China (defaults to the global endpoint)
export MINIMAX_REGION="cn"
# Optional: pick MiniMax-M3 instead of the default MiniMax-M3.1-Flash
export MINIMAX_MODEL="MiniMax-M3"

Or use OpenAI compatible API:

export OPENAI_API_KEY="your-openai-api-key"
# or
MINIKODE_API_KEY="your-api-key"
MINIKODE_BASE_URL="https://your-api-provider.com/v1"
MINIKODE_MODEL="your-model-name"

Run Mini-Kode

# Interactive mode (launch UI)
mini-kode

# Non-interactive mode (direct execution)
mini-kode "help me fix the bug in auth.ts"

🔧 Development Quick Start

Prerequisites

• Bun
• pnpm

Install Dependencies

pnpm install

Development Commands

# Development mode with file watching
pnpm run dev

# Build
pnpm run build

# Test
pnpm run test

📖 Learning Resources

Want to dive deeper into the system architecture? Check out docs/README.md for complete system documentation and architecture explanations.

📚 Project Analysis

For a comprehensive code analysis and walkthrough, visit Mini-Kode Deep Analysis - an in-depth exploration of the codebase architecture, design patterns, and implementation details.

🧠 Project Memory

Mini-Kode automatically uses AGENTS.md file in your project root to provide context-aware assistance:

• Automatic Context: System reads AGENTS.md to understand your project
• Customizable: Edit AGENTS.md to include project-specific information
• Persistent Memory: Maintains project context across sessions

🏗️ Project Structure

src/
├── tools/          # Tool system and individual tools
├── ui/             # Ink-based CLI interface components
├── llm/            # LLM client and streaming integration
├── permissions/    # Two-layer permission system
├── config/         # Configuration management
├── cli/            # CLI framework and commands
├── agent/          # Core agent logic
├── sessions/       # Session management
└── utils/          # Shared utilities

🛠️ Tech Stack

• TypeScript - Static type checking
• pnpm - Package management
• Ink - React terminal UI
• OpenAI SDK - LLM integration (supports DeepSeek/OpenAI/compatible APIs)
• Vitest - Testing framework
• Zod - Runtime type validation
• Commander - CLI framework

🚧 Future Plans

1. Session Persistence and Resume - Save and restore agent sessions
2. LLM Built-in Tool Integration - Support for LLM's native tool capabilities (note: DeepSeek currently doesn't support web search tools)
3. Image Input Support - Process and analyze image inputs
4. Sub Agents Functionality - Hierarchical agent delegation
5. Reasoning Model Support - Integration with reasoning-focused models
6. Tool Call Message Streaming - Real-time streaming of tool execution
7. Context Caching - Smart caching of conversation context to reduce token usage

📚 References

This project was inspired by and references the following resources:

• Building an Agent - Guide on building AI agents
• Building an Agentic System - Comprehensive guide to building agentic systems
• System and Tool Prompts - System prompts and tool prompts for coding agent
• Neovate Code - Todo tool prompt
• Claude Code - UX reference for CLI interface design