Skip to main content
Glama
yulinlina

ctxbleach

by yulinlina
README.md
<div align="center">

# `ctxbleach`

### Local CLI and MCP server that bleaches secrets from logs, files, and diffs before AI agents see them.

![License](https://img.shields.io/badge/license-MIT-blue.svg) ![Language](https://img.shields.io/badge/language-python-green.svg) ![Status](https://img.shields.io/badge/status-active-success.svg) ![Python](https://img.shields.io/badge/python-3.10%2B-blue) ![License](https://img.shields.io/badge/license-MIT-green) ![MCP](https://img.shields.io/badge/MCP-stdio-orange)

<img src="demo.gif" alt="Demo" width="700" />

</div>

---

## 🎯 Why?

Trending agent-context projects focus on giving agents more code and memory, while guardrail tools mostly block commands. Developers still need a tiny local middleware that transforms raw logs, env files, and command output into safe, token-budgeted context before it reaches an LLM. Existing secret scanners are CI-oriented and do not provide interactive redaction placeholders, MCP tools, or context budgeting.

**Target audience:** Developers and platform engineers using Claude Code, Cursor, Codex, or MCP-enabled agents who need to share logs, .env files, stack traces, and CI output without leaking credentials.

## ✨ Features

- ✨ **Regex-based redaction for AWS keys, GitHub/Slack tokens, JWTs, bearer headers, URL passwords, private keys, and generic secret assignments**
- ✨ **Stable placeholders and masked scan output so no secret values are echoed back**
- ✨ **Token-budgeted truncation with head or tail preservation for large logs**
- ✨ **CLI commands for scan, redact, and MCP stdio serving**
- ✨ **Zero-dependency Python implementation that can be dropped into agent workflows**

## 🚀 Quick Start

```bash
# Install
pip install ctxbleach

# Run
ctxbleach --help
```

## 📦 Installation

### From Source

```bash
git clone https://github.com/YOUR_USERNAME/ctxbleach.git
cd ctxbleach
```

```bash
# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate

# Install in development mode
pip install -e ".[dev]"

# Run tests
pytest -v
```

## 🎬 Demo

The GIF above was recorded using [Charm VHS](https://github.com/charmbracelet/vhs):

```bash
vhs < demo.tape
```

## 📖 Usage

```bash
# Show help
ctxbleach --help

# Common usage examples
ctxbleach --example
```

## 🏗️ Architecture

```mermaid
graph LR
    A[Input] --> B[Core Engine]
    B --> C[Output]
    B --> D[Plugins]
    D --> E[Extensions]
```

## 🤝 Contributing

Contributions are welcome! Please:

1. Fork the repo
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request

## 📄 License

MIT © 2026 — See [LICENSE](LICENSE) for details.

---

<div align="center">

**If this project helped you, please ⭐ star it!**

[Made with ❤️ and AI](https://github.com)

</div>

Maintenance

ActivitySlowing
ResponsivenessNo issues