JSPM

  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 37
  • Score
    100M100P100Q83036F
  • License MIT

Fast context extractor for AI coding. No install needed: npx @spahmonk/ctx-lite

Package Exports

  • @spahmonk/ctx-lite
  • @spahmonk/ctx-lite/bin/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@spahmonk/ctx-lite) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

ctx-lite 🚀

Fast context extractor for AI coding with cross-platform support

Extract code context with 87% compression for Claude, Copilot, and other AI models. Perfect for MCP integration.


⚡ Quick Install (30 seconds)

Linux / macOS

curl -fsSL https://raw.githubusercontent.com/spahmonk/ai-helpers/main/scripts/install.sh | bash

Windows (PowerShell)

powershell -Command "iex ((New-Object System.Net.WebClient).DownloadString('https://raw.githubusercontent.com/spahmonk/ai-helpers/main/scripts/install.ps1'))"

npm (Node.js 18+)

npm install -g @spahmonk/ctx-lite

Verify

ctx-lite --version  # Should print: ctx-lite 0.1.0

👉 Full installation guide →


💡 Usage Examples

# Read and compress a file
ctx-lite read src/main.rs

# Show directory tree with compression info
ctx-lite tree ./src

# Search for text or regex patterns
ctx-lite search "function_name"

# Run diagnostics
ctx-lite doctor

📦 Features

  • 87% Compression - Exceed lean-ctx baseline
  • Cross-Platform - Linux, macOS, Windows
  • MCP Compatible - Use as Model Context Protocol server
  • Fast - <1s per session
  • Secure - Path jail, audit logging
  • ML Optimized - Adaptive compression modes

📚 Documentation


🏗️ Development

Build from source

git clone https://github.com/spahmonk/ai-helpers.git
cd ai-helpers
cargo build --release

Run tests

cargo test --workspace

Code quality

cargo fmt --all --check

📊 Benchmarks

Metric Result
Session Compression 87%
Token Reduction 66-75%
Processing Time <1s per session
Cache Hit Rate 94%+

🔐 Security

  • Path jail prevents directory traversal
  • Git config injection prevention
  • Audit log with redaction
  • SHA256 content hashing

📦 Release Information

  • Version: 0.1.0
  • Status: Production Ready
  • Tests: 258/258 passing ✓
  • Platforms: Linux, macOS, Windows
  • License: MIT (see LICENSE)

All releases →


🤝 Contributing

Contributions welcome! Please:

  1. Fork the repository
  2. Create a feature branch
  3. Write tests first (TDD)
  4. Ensure all tests pass: cargo test --workspace
  5. Submit a pull request

❓ Support


📄 License

MIT License - see LICENSE file


Made with ❤️ for AI-assisted development