Safe Colab CLI
Enable AI agents to analyze your sensitive data remotely — without ever copying it.
A command-line tool that launches a sandboxed Python environment on your machine (or in the cloud), registers it as a remote service via Hypha, and lets AI agents execute code through a guardian agent that enforces your sensitivity policy.
Key Features
- Guardian Agent — LLM-powered security checks validate code before execution and output before return
- Sensitivity Contract — Define protected columns, minimum aggregation, and allowed operations in a README.md
- Live Dashboard — Web dashboard with real-time activity log and operation stats
- Protected Audit Logs — Full audit trail in
~/.safe-colab/logs/, protected from sandboxed code - Sandbox Isolation — nono (macOS/Linux) or Docker restricts kernel filesystem access
- Remote Hosting — Upload dataset once, cloud pods spin up on demand (no laptop needed)
- Zero Config for Agents — Agents call
get_skill_mdvia curl to learn the API. No SDK, no token needed.
Quick Start
Local Mode (data stays on your machine)
pip install safe-colab-cli
safe-colab login --server-url https://hypha.amun.ai
safe-colab start --data-dir ./my-data --guardian-url https://guard.amun.ai
Remote Mode (upload once, pods on demand)
pip install safe-colab-cli
safe-colab login --server-url https://hypha.amun.ai
safe-colab deploy --data-dir ./my-data --guardian-url https://guard.amun.ai
# → Uploads dataset, registers app. Share the App ID with your AI agent.
# → Pods spin up automatically when an agent calls start().
Use the Amun AI production servers
Safe Colab talks to two services and both must point at the Amun AI
deployment (older installs and some docs default to an aicell.io instance):
| Service | Amun AI URL | How to set it |
|---|---|---|
| Hypha (registers your kernel; chosen at login) | https://hypha.amun.ai |
safe-colab login --server-url https://hypha.amun.ai |
| Guardian (validates every code/output) | https://guard.amun.ai |
--guardian-url https://guard.amun.ai on start/deploy |
The Hypha server is fixed at login time — if you logged in against a
different server, re-run safe-colab login --server-url https://hypha.amun.ai
to overwrite the saved credentials in ~/.safe-colab/.env. You can also set
both via environment (persist them in your shell profile):
export HYPHA_SERVER_URL=https://hypha.amun.ai
export SAFE_COLAB_GUARDIAN_URL=https://guard.amun.ai
Verify the guardian before a session or demo (accepts the Terms of Use, then runs a built-in safe/blocked suite):
safe-colab test-guardian --url https://guard.amun.ai --accept-terms
# → Health: OK … 4/4 tests passed
Documentation
See the docs site or the GitHub project for full documentation.
License
Copyright 2024-2026 Amun AI AB. All rights reserved.
This software is proprietary and confidential. No part of this software may be reproduced, distributed, or transmitted in any form or by any means without the prior written permission of Amun AI AB. Unauthorized copying, modification, distribution, or use of this software is strictly prohibited.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file safe_colab_cli-0.18.0.tar.gz.
File metadata
- Download URL: safe_colab_cli-0.18.0.tar.gz
- Upload date:
- Size: 155.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.12.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9ee52753cf736323a60f181b493f0bb644b49afb45ab180a524fce6afe5c4803
|
|
| MD5 |
eabd087a85e27d77e5dae649ee902f45
|
|
| BLAKE2b-256 |
01ae07b96e950648cc1e3f0be78803816f719bda31306b630fa6218e7c0bd5b3
|
File details
Details for the file safe_colab_cli-0.18.0-py3-none-any.whl.
File metadata
- Download URL: safe_colab_cli-0.18.0-py3-none-any.whl
- Upload date:
- Size: 102.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.12.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e72794b0269efd015ee315a6deb87c9109f082981c3b9eae34adec4c014ff83a
|
|
| MD5 |
dcb1ff901b04c144c0dae20749ccf698
|
|
| BLAKE2b-256 |
68139e61f037f8e76335cedb68d3780571c4064982cb6e42dbe3c359735c2be7
|