Metadata-Version: 2.4
Name: bubble-agent
Version: 0.1.0
Summary: Run your coding agent in a bubble.
Project-URL: Homepage, https://github.com/ak1ra-lab/bubble-agent
Project-URL: Repository, https://github.com/ak1ra-lab/bubble-agent
Project-URL: Documentation, https://ak1ra-lab.github.io/bubble-agent/
Author-email: ak1ra <git@ak1ra.xyz>
License-Expression: MIT
License-File: LICENSE
Classifier: Development Status :: 4 - Beta
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Python: >=3.11
Requires-Dist: argcomplete>=3.6.3
Description-Content-Type: text/markdown

# bubble-agent

[![GitHub Actions Workflow Status](https://img.shields.io/github/actions/workflow/status/ak1ra-lab/bubble-agent/.github%2Fworkflows%2Fpublish-to-pypi.yaml)](https://github.com/ak1ra-lab/bubble-agent/actions/workflows/publish-to-pypi.yaml)
[![PyPI - Version](https://img.shields.io/pypi/v/bubble-agent)](https://pypi.org/project/bubble-agent/)
[![Docs](https://img.shields.io/badge/docs-online-0a7ea4)](https://ak1ra-lab.github.io/bubble-agent/)

> This project is inspired by [cyunrei/opencode-bwrap](https://github.com/cyunrei/opencode-bwrap).

Run your coding agent in a bubble.

Uses [bubblewrap](https://github.com/containers/bubblewrap) to sandbox coding agents with configurable bind mounts and virtual workspace (`.code-workspace`) support.  Sandbox arguments are passed via ``--args <fd>`` for clean process listings, and ``/etc/profile`` is automatically patched to prevent login shells from resetting the custom ``PATH``.

By default, the sandbox wraps [opencode](https://github.com/anomalyco/opencode). Use `--bin` to run a different coding agent.

## Quick Start

```shell
git clone https://github.com/ak1ra-lab/bubble-agent.git
cd bubble-agent
just install

bubble-agent                              # runs opencode by default
bubble-agent ~/my-project                 # work in a specific directory
bubble-agent --dry-run                    # preview the bwrap command
```

See [Documentation](https://ak1ra-lab.github.io/bubble-agent/) for full usage, configuration, and workspace features.
