Skip to main content

Container wrapper for running AI coding agents in isolated, secure containers

Project description

Paude

Run AI coding agents in secure containers. They make commits, you pull them back.

Supported Agents

Agent Flag Status
Claude Code --agent claude (default) Supported
Cursor CLI --agent cursor Supported
Gemini CLI --agent gemini Supported

Note: Your chosen agent must be installed and working on your local machine first.

Why Paude?

  • Isolated execution: Your agent runs in a container, not on your host machine
  • Safe autonomous mode: Enable --yolo without fear — the agent can't send your code anywhere
  • Git-based workflow: The agent commits inside the container, you git pull the changes
  • Run anywhere: Locally with Podman or Docker, remotely via SSH, or on OpenShift

Demo

asciicast

The demo shows Claude Code, but the workflow is identical with other agents.

Quick Start

Prerequisites

Your agent: Claude Code, Cursor CLI, or Gemini CLI installed and working locally.

Podman or Docker: Install Podman or Docker (for local backend).

Google Cloud SDK: gcloud auth application-default login

Environment variables (find your project ID in Google Cloud Console):

Claude Code:

export CLAUDE_CODE_USE_VERTEX=1
export ANTHROPIC_VERTEX_PROJECT_ID=your-project-id
export GOOGLE_CLOUD_PROJECT=your-project-id

Cursor CLI:

agent login  # or set CURSOR_API_KEY=your-api-key

macOS note: On Mac hosts, CURSOR_API_KEY is the simplest authentication method. Without it, each paude session requires a separate browser-based OAuth login via agent login inside the container.

Gemini CLI:

export GOOGLE_CLOUD_PROJECT=your-project-id

Install

uv tool install paude

First run: Paude pulls container images on first use. This takes a few minutes; subsequent runs start immediately.

Your First Session

# Claude Code (default)
cd your-project
paude create --yolo --git my-project

# Cursor CLI
paude create --agent cursor --yolo --git my-project

# Gemini CLI
paude create --agent gemini --yolo --git my-project

# Connect to the running session
paude connect my-project

# Pull the agent's commits (use your branch name):
git pull paude-my-project main

You'll know it's working when: paude connect shows the agent interface, and git pull brings back commits the agent made.

Passing a Task

paude create --yolo my-project -a '-p "refactor the auth module"'

Or just start the session and type your request in the agent interface.

Something Not Working?

  • Run paude --help for all options and examples
  • Run paude list to check session status
  • Use paude create --dry-run to verify configuration
  • Use paude start -v for verbose output (shows sync progress)
  • Check that your gcloud credentials are valid: gcloud auth application-default print-access-token

Learn more:

How It Works

Your Machine                    Container
    |                              |
    |-- git push ----------------▶ |  Agent works here
    |                              |  (network-filtered)
    ◀-- git pull -----------------|
    |                              |
  • Git is the sync mechanism — your local files stay untouched until you pull
  • --yolo is safe because network filtering blocks the agent from sending data to arbitrary URLs
  • The agent can only reach its API (e.g., Vertex AI) and package registries (e.g., PyPI) by default

Install from Source

git clone https://github.com/bbrowning/paude
cd paude
uv venv --python 3.12 --seed
source .venv/bin/activate
pip install -e .

Requirements

  • Python 3.11+ (for the Python package)
  • Your chosen agent CLI installed locally (Claude Code, Cursor CLI, or Gemini CLI)
  • Podman or Docker (for local backend)
  • OpenShift CLI oc (for OpenShift backend)
  • Google Cloud SDK configured (gcloud auth application-default login)

Development

See CONTRIBUTING.md for development setup, testing, and release instructions.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

paude-0.13.0.tar.gz (279.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

paude-0.13.0-py3-none-any.whl (143.5 kB view details)

Uploaded Python 3

File details

Details for the file paude-0.13.0.tar.gz.

File metadata

  • Download URL: paude-0.13.0.tar.gz
  • Upload date:
  • Size: 279.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for paude-0.13.0.tar.gz
Algorithm Hash digest
SHA256 1e63cff5a41904be5ca3945c0fa728550f46f532b57be0d3fb367aa6336a916c
MD5 708e1e68fa68b325231056af42d8c1a2
BLAKE2b-256 521c83aa41a47bdc76d78f2385e6636bcdee20a8d76c0565b1781da3effa0312

See more details on using hashes here.

Provenance

The following attestation bundles were made for paude-0.13.0.tar.gz:

Publisher: release.yml on bbrowning/paude

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file paude-0.13.0-py3-none-any.whl.

File metadata

  • Download URL: paude-0.13.0-py3-none-any.whl
  • Upload date:
  • Size: 143.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for paude-0.13.0-py3-none-any.whl
Algorithm Hash digest
SHA256 29a1977800d6cb4f9aed14739affe1b3ae430fd5cc44607dc13aeed9dd2f046d
MD5 bd331c3a8ec057eb7e78d4d01cfe12fa
BLAKE2b-256 49b0a8cb7bbc55a7032b70aa7786d7b5a027a48fcfe2d827d1d4a354e15f8b2b

See more details on using hashes here.

Provenance

The following attestation bundles were made for paude-0.13.0-py3-none-any.whl:

Publisher: release.yml on bbrowning/paude

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page