amdb: AI Context Generator
⚡ The Context Problem
AI coding assistants (Cursor, Windsurf, Claude) are powerful, but they are blind. They only see the files you open. They lack the deep, structural understanding of your entire codebase that you have in your head.
amdb (Agent Memory Database) solves this. It scans your local project, builds a vector index of your code, and generates a single, highly-optimized Markdown context file. Feed this file to your AI, and watch it instantly understand your project's architecture, dependencies, and logic.
📦 Installation
Install amdb directly from the source.
# Clone and install locally
Note: Ensure you have the Rust toolchain installed (
cargo).
🚀 Quick Start
1. Initialize Project
Run this in your project root. amdb will scan your code (Rust, Python, JS/TS), extract symbols, and build a vector database in a hidden .database/ folder.
2. Generate Context
Create a full project summary. This generates .amdb/context.md, which contains a compressed map of your entire codebase.
🔥 Pro Tip: Drag and drop .amdb/context.md into your AI chat (Cursor/Claude) to give it "God Mode" understanding of your project.
🧠 Advanced Usage: Focus Mode
For large projects, a full context might be too big. Use Focus Mode to generate a summary relevant to a specific feature or bug. amdb uses vector search to find the most relevant files.
# Example: generating context for authentication logic
This creates a targeted summary (e.g., in .amdb/) containing only the symbols and files relevant to "login authentication jwt".
🛠 Supported Languages
amdb uses robust Tree-sitter parsers to fully understand the syntax and structure of:
- Rust (
.rs) - Python (
.py) - JavaScript (
.js) - TypeScript (
.ts,.tsx)
📝 Git Configuration
amdb generates local files that should usually be ignored by Git.
Add this to your .gitignore:
.database/
.amdb/
<p align="center">
Generated by amdb • The Missing Memory for AI Agents
</p>