Metadata-Version: 2.5
Name: ai-container
Version: 0.23.0
Summary: AI - Tool/Agent isolation
Requires-Python: >=3.13
Requires-Dist: click
Requires-Dist: podman>=5.8.0
Requires-Dist: rich-click>=1.8.0
Requires-Dist: rich>=14.3.1
Description-Content-Type: text/markdown

# AI-Container

Podman based container for isolating AI tooling for a individual project.

## Context

In the past, I have repeatedly observed and experienced coding agents accessing or using files and content which they either weren't supposed to, or even technically "did not have access to."

On one occasion, for example, file access was explicitly restricted (e.g., the path was blocked). However, the agent exploited its ability to run bash commands, using them to traverse and scan the restricted paths instead of relying on standard read/write methods.

For this reason, I believe it is essential to implement clear restrictions or a contextual sandbox that is shared with the AI, and which it cannot as easily circumvent by simply invoking a different command.


## Prerequisites

- **Podman** (>= 5.0) - Container runtime. [Install](https://podman.io/docs/installation)
- **Python** (>= 3.13) - Required for the CLI. [Install](https://www.python.org/downloads/)
- **uv** - Used to install and run the CLI. [Install](https://docs.astral.sh/uv/)

Image builds and volume creation are performed through the
[Podman Python SDK](https://github.com/containers/podman-py), which talks to
the Podman service socket. Make sure the socket is running:

```bash
systemctl --user enable --now podman.socket
```


## Installation

Install the `ai-container` package:

```bash
uv tool install ai-container
```

Or from source:

```bash
git clone https://github.com/yourusername/ai-container.git
cd ai-container
uv tool install .
```

The `ai` command will then be available.

## Usage

### Basic Commands

```bash
ai agent pi /path/to/project        # Run PI coding agent
ai agent opc /path/to/project       # Run OpenCode coding agent
ai agent claude /path/to/project    # Run Claude Code
ai agent aic /path/to/project       # Run aichat
ai agent llm /path/to/project       # Run llm
ai shell /path/to/project           # Interactive shell in container
```

`ai agent <tool> [paths...] [-- args...]` is the single entry point for every
tool. Valid tools: `pi`, `opc`, `claude`, `aic`, `llm`.

Pass additional arguments to the tool after `--`:
```bash
ai agent pi /path/to/project -- --verbose --model claude-3-sonnet
```

### Mounting Folders

The paths you pass decide what the container sees in `/workspace`:

```bash
ai shell                           # nothing mounted, empty /workspace
ai shell ./app                     # contents of ./app  -> /workspace
ai shell ./mount1 ../mount2        # ./mount1           -> /workspace/mount1
                                   # ../mount2          -> /workspace/mount2
```

When you pass several paths, each folder is mounted under its own name, so
folder names must be distinct.

### Rebuilding the Container Image

The container image is built automatically on first use via the Podman SDK.
When you want to pull in the latest tool versions, force a rebuild with the
`image rebuild` command:

```bash
ai image rebuild                  # rebuild the default (configured) image
ai image rebuild pi pi-python     # rebuild several images, parents first
ai image rebuild pi,pi-python     # same, comma-separated
ai image rebuild --all            # rebuild every image, parents first
ai image rebuild --deep pi        # also rebuild parents (claude, base)
ai image rebuild --no-cache pi    # ignore the layer cache, fetch latest tools
```

By default, build steps whose instructions did not change are reused from the
layer cache, so tools installed by e.g. `npm install -g` are **not** updated.
Use `--no-cache` to re-run every step. Only the named images are rebuilt,
their parent images are built only if missing. Add `--deep` to rebuild the
whole parent chain as well (combine both for a complete refresh:
`ai image rebuild --deep --no-cache pi-python`).

### Custom Environments

Need a specific toolchain (Rust, Go, an extra editor, ...)? Define a **custom
environment**: a thin image built `FROM aic:base` that adds your tooling on top
of everything the base image already provides.

Select an environment with the `-e/--env` option of `shell` and `agent`;
`image rebuild` takes image names as arguments:

```bash
ai shell -e rust .            # shell in the rust environment
ai agent -e rust pi .         # run pi in the rust environment
ai image rebuild rust         # (re)build the rust image (FROM aic:base)
ai image rebuild rust,go pi   # environments and built-in images can be mixed
```

Manage environment definitions with the `env` group:

```bash
ai env list                   # show environments and whether images are built
ai env new rust               # scaffold a Containerfile (FROM aic:base)
ai env new rust --edit        # scaffold and open it in $EDITOR
ai env edit rust              # edit the Containerfile
ai env path rust              # print the Containerfile path
ai env remove rust --purge    # delete the definition (and its image)
```

Definitions live under `~/.config/ai-container/environments/<name>/`
(honoring `XDG_CONFIG_HOME`). The directory is also the build context, so you
can `COPY` local files into your image. A scaffolded `Containerfile` looks like:

```dockerfile
# rust environment -- extends the ai-container base image.
FROM aic:base

RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \
    | sh -s -- -y --default-toolchain stable
ENV PATH="/root/.cargo/bin:${PATH}"

WORKDIR /workspace
```

Without `-e`, the default `base` environment is used. Persistence volumes
(`config`, `state`, `share`, `pi-config`, `claude`) are shared across all
environments, so credentials and config are entered once and work everywhere.

### Config Files

Defaults for `-e/--env` and the global flags (`--log-level`, `--dryrun`) can be set
in a TOML config file, so you don't have to repeat them on every invocation.
Files are merged from several sources, **highest precedence first**:

1. `./.ai-container.toml` — project-local, in the current working directory
2. `~/.config/ai-container/config.toml` — user config (honors `XDG_CONFIG_HOME`)
3. `~/.ai-container.toml` — home dotfile
4. Built-in defaults

Command-line flags always override config files. Each layer only needs to set
the keys it cares about; the rest fall through to the next layer.

```toml
# .ai-container.toml
env = "rust"        # default environment
log_level = "DEBUG" # one of: DEBUG, INFO, WARNING, ERROR, CRITICAL
dryrun = false
```

### Provided Tools
- **[PI](https://shittycodingagent.ai)** - Coding agent for generation, analysis, and refactoring
- **[OpenCode](https://opencode.ai)** - AI-powered coding assistant
- **[Claude Code](https://www.anthropic.com/claude-code)** - Anthropic's official coding agent
- **[aichat](https://github.com/sigoden/aichat)** - Interactive AI chat interface
- **[llm](https://github.com/simonw/llm)** - Command-line tool for LLM interaction

### Configuration & Persistence

**First run:** The container image is built (one-time, takes a few minutes).

**Tools use their standard configuration methods** (within the container):
- aichat: `~/.config/aichat/config.toml`
- llm: `~/.config/llm/` + environment variables
- PI: `~/.pi/`
- OpenCode: `~/.config/opencode/`
- Claude Code: `~/.claude/`

**Configuration persists automatically across all runs and containers** through named Podman volumes (`config`, `state`, `share`, `pi-config`, `claude`). Configure once, use everywhere:

```bash
# First run: setup credentials
ai shell /path/to/project
# Inside container: aichat, llm keys set openai <key>, etc.

# Subsequent runs: credentials available automatically
ai agent pi /path/to/project
```

## Other/Previous Work
* [agent-containers](https://github.com/faileon/agent-containers)
* [agent-container](https://github.com/asfaload/agents_container)
* [opencode-dockerized](https://github.com/glennvdv/opencode-dockerized/tree/main)
