aiBox
╔═══════════════════════════════════════════════════════════════╗
║ ║
║ █████╗ ██╗ ██████╗ █████╗ ██╗ ██╗ ║
║ ██╔══██╗██║ ██╔══██╗██╔══██╗░╚██╗██╔╝ ║
║ ███████║██║ ██████╔╝██║░░██║░░╚███╔╝░ ║
║ ██╔══██║██║ ██╔══██╗██║░░██║░░██╔██╗░ ║
║ ██║░░██║██║ ██████╔╝╚█████╔╝ ██╔╝╚██╗ ║
║ ╚═╝░░╚═╝╚═╝ ╚═════╝░░╚════╝░ ╚═╝░░╚═╝ ║
║ ║
║ Container-Based Multi-AI Development Environment ║
║ ║
╚═══════════════════════════════════════════════════════════════╝
Container-Based Multi-AI Development Environment
Multi-AI development environment with Python-based tooling, comprehensive testing, and beautiful CLI.
Documentation | Configuration | Architecture | Agents Guide
Features
- 🤖 Multi-AI Support - Claude, Gemini, and OpenAI Codex
- 🐳 Docker-Based - Isolated, reproducible development environments
- 🔧 Profiles - Python, Node.js, Rust, Go, plus utility profiles (sudo, git)
- 🚀 Beautiful CLI - Rich terminal output with progress indicators and tables
- 🔌 Parallel Slots - Run multiple AI containers simultaneously
- ♻️ Shared Base Images - Reuse profile layers across providers; only provider CLIs rebuild
- 📦 Profile System - Declarative YAML-based language/tool configurations
- ⚙️ Type-Safe Config - Pydantic validation with helpful error messages
- 🔄 Session Continuation - Reuse the same slot container by default; optional one-off mode with
--auto-delete
Quick Start
# Install aibox
pip install aibox-cli
# or with uv (recommended)
uv pip install aibox-cli
# Navigate to your project
cd my-project
# Initialize the project (select profiles and versions)
aibox init
# Start AI development environment (interactive slot/provider wizard)
aibox start
New to aibox? See the Getting Started Guide for detailed instructions.
Installation
Prerequisites
- Docker - Running and accessible (Install Docker)
- Python 3.11+ - For the CLI tool (Download Python)
- Authentication:
- Claude: OAuth authentication (authenticates in browser on first use)
- Gemini & OpenAi: aibox launches a short-lived login container during slot creation to capture an OAuth session
Install via pip
# Recommended: use uv
uv pip install aibox-cli
# Or use pip
pip install aibox-cli
# Verify installation
aibox --version
Install from Source
git clone https://github.com/fogXploit/aibox.git
cd aibox
uv pip install -e ".[dev]"
See Getting Started for detailed installation instructions.
Shell Autocomplete
aibox supports shell autocomplete for Bash, Zsh, Fish, and PowerShell. Once enabled, you can press TAB to autocomplete.
Install Autocomplete
# Install completion for your shell
aibox --install-completion
# Restart your terminal
# Then try it out:
aibox profile info <TAB> # Shows: go nodejs python rust python:3.11 ...
aibox start --slot <TAB> # Shows configured slot numbers
Supported Shells
- Bash - Automatically detected and configured
- Zsh - Automatically detected and configured
- Fish - Automatically detected and configured
- PowerShell - Automatically detected and configured
Note: If autocomplete doesn't work after installation, ensure you've restarted your terminal or sourced your shell configuration file (e.g., source ~/.bashrc or source ~/.zshrc).
Usage
Essential Commands
# Initialize project and select profiles
aibox init
# Start AI environment (interactive provider + slot wizard)
aibox start
# Reuse a specific slot (preserves container state)
aibox start --slot 2
# One-off session (stop and remove container on exit)
aibox start --auto-delete
# Slots
aibox slot list
aibox slot add # pick slot + provider by number
aibox slot cleanup # remove stopped slot containers and slot configs
# Profiles
aibox profile list
aibox profile info python
# Config
aibox config show
aibox config validate
aibox config edit
# Status
aibox status
See Getting Started for workflow examples.
Session Continuation & Reuse
- aibox reuses the same container for a slot by default. Start again with the same
--slotto keep your tools and filesystem state. - When you exit the AI CLI, the container is stopped but preserved. Use
--auto-deletefor a one-off session (container is removed when the CLI exits). - Provider notes:
- Claude and Gemini persist auth/state via their mounted config directories (!TODO)
- OpenAI Codex: container reuse preserves CLI config. To continue a Codex conversation, start
with
aibox start --slot <n> --resumeto launchcodex resume(slot must already have a Codex session); omit--resumeto start a fresh Codex session in that slot.
Profiles
Built-in profiles:
python:3.11|3.12|3.13- Python with uv package managernodejs:20- Node.js with npm global configuredgo:1.21|1.22|1.23- Go with modulesrust:stable|beta|nightly|1.75|1.76|1.77- Rust with cargo/rustfmt/clippysudo:1- Passwordless sudo for the aibox usergit:latest- Git client
Profile definitions live in aibox/profiles/definitions/*.yml; customize or add your own as needed.
TODO: More will be added
Documentation
- Getting Started - Installation and first project guide
- Configuration Reference - Complete YAML configuration docs
- Architecture - Technical architecture details
- CONTRIBUTING - Development and contribution guide
Development
Setup
# Clone repository
git clone https://github.com/fogXploit/aibox.git
cd aibox
# Install with dev dependencies
uv pip install -e ".[dev]"
# Install pre-commit hooks
pre-commit install
Running Tests
# All tests
pytest
# Unit tests only
pytest tests/unit
# With coverage
pytest --cov=aibox --cov-report=html
Code Quality
# Lint and format
ruff check aibox/
ruff format aibox/
# Type checking
mypy aibox/
# Run all checks
pre-commit run --all-files
Architecture
aibox/
├── cli/ # CLI commands (Typer)
├── providers/ # AI provider implementations
├── containers/ # Docker management (Docker SDK)
├── profiles/ # Profile system (YAML-based)
├── config/ # Configuration (Pydantic models)
└── utils/ # Utilities (logging, errors)
See ARCHITECTURE.md for details.
Roadmap
v0.1
- ✅ Claude CLI support
- ✅ Gemini CLI support
- ✅ OpenAI CLI support
- ✅ 4+ language profiles
- ✅ Slot system (parallel containers)
- ✅ YAML configuration
- ✅ Beautiful CLI with Rich
v0.2
- ✅ Additional profiles
- ✅ AI provider integrations enhanced
- ✅ user friendly login workflow for Gemini
- ✅ status overview added
v0.3 (Current)
- ✅ persistence & one-time container support
- ✅ cleanup workflows
- ✅ login helper for codex
- ✅ codex-cli resume support
v0.4+
- TODO
Contributing
Contributions welcome! See CONTRIBUTING.md for guidelines.
Adding a New Profile
- Create
aibox/profiles/definitions/myprofile.yml - Add tests in
tests/unit/test_profiles.py - Update documentation
- Submit PR
Troubleshooting
Docker Not Found
# Install Docker Desktop
# https://docs.docker.com/get-docker/
Gemini Login Helper
# Gemini uses OAuth. When you add a Gemini slot, aibox runs a short-lived
# host-network container to execute `gemini login` so the random callback port works.
# Follow the printed URL in your browser; the session is stored under the slot's .gemini/ directory.
OpenAI Login Helper
# OpenAI Codex also uses OAuth. aibox now runs a short-lived host-network container
# to execute `codex login` when a slot needs authentication, so the main container
# doesn't keep a lingering 1455 port binding. The session is stored under the slot's
# .codex/ directory.
Authentication Issues (Claude/OpenAI)
# Claude and OpenAI use OAuth - no API keys needed
# If authentication fails:
# 1. Ensure Docker ports are accessible (54545 for Claude, 1455 for Codex)
# 2. Check your browser isn't blocking popups
# 3. Try running the CLI inside the container again - it will re-prompt
Permission Denied
# Add user to docker group (Linux)
sudo usermod -aG docker $USER
# Log out and back in
License
MIT License - see LICENSE for details.
Acknowledgments
- Built with Typer, Rich, and Docker SDK
- Thanks to all contributors
Links
- Documentation: https://github.com/fogXploit/aibox/tree/main/docs
- PyPI: https://pypi.org/project/aibox-cli/
- GitHub: https://github.com/fogXploit/aibox
- Issues: https://github.com/fogXploit/aibox/issues
- Discussions: https://github.com/fogXploit/aibox/discussions
Built with ❤️ for AI-powered development
Metadata
Release files for aibox-cli 0.3.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| aibox_cli-0.3.3.tar.gz | 104.9 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| aibox_cli-0.3.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 177.0 kB
Release files / aibox_cli-0.3.3.tar.gz
| Download URL | aibox_cli-0.3.3.tar.gz |
|---|---|
| Size | 104.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
117eb0f74bd8de13c9ba51c8f5433d7e8023d31d4c4b782d4715ef72e3c86ffe
|
|
BLAKE2b-256 checksum How to use checksums |
bec4de3b86916b5d65bedd86716fa7e4229fc6f5747b899f9b6de557f5f95a70
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 17, 2026.
Transparency logRelease files / aibox_cli-0.3.3-py3-none-any.whl
| Download URL | aibox_cli-0.3.3-py3-none-any.whl |
|---|---|
| Size | 72.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
976e39c410e301f5cd01710ff5bfcc875fe8fd285d40cb42c45756d026e3af6b
|
|
BLAKE2b-256 checksum How to use checksums |
f14e5b28403755f66a47768976c5464b7852c66722373f15ac74b173c024a165
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 17, 2026.
Transparency logSecurity for aibox-cli 0.3.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for aibox_cli-0.3.3.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 17, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.