Skip to main content

Aegis AI — Privacy-First Chat Interface

Aegis AI is a privacy-first chat application that de-identifies sensitive information before sending prompts to cloud-based LLMs (like Gemini or Claude), then reconstructs the original data into the response — ensuring your Personally Identifiable Information (PII) never leaves your device.

Why Aegis AI?

When you chat with standard AI models, your private data—names, addresses, financial details, and company information—is often sent directly to cloud servers. Aegis AI introduces a Local Privacy Shield that intercepts your message, removes the sensitive data, and replaces it with secure placeholders before it ever hits the internet. When the AI responds, Aegis restores your data locally, giving you a seamless, private experience.

Getting Started

Aegis AI relies on a secure local server running on your machine to process text and protect your privacy.

There are two ways to run the Aegis Privacy Server:

Option 1: Standard Python Installation (Recommended)

If you have Python installed, you can simply install our secure local package from PyPI.

# 1. Install the official PyPI package (this automates pulling the necessary local models)
pip install aegis-local

# 2. Start the local server
aegis-server

The server will boot up and securely listen on port 3001.

Option 2: Standalone Executable

If you do not have Python installed or prefer not to use the terminal, download the standalone binary (available for macOS, Windows, and Linux). Once downloaded, simply execute the file and the server will run in the background.

Usage

Once the local privacy server is running (aegis-server), open the Aegis AI web interface. The interface will automatically connect to your local server on port 3001, enabling the Privacy Shield for all your conversations.

How It Works (High Level)

  1. You type a prompt.
  2. Local Shield: The Aegis local server automatically detects and strips sensitive data (names, addresses, IDs).
  3. Cloud Processing: A sanitized prompt is sent to the cloud LLM (Gemini or Claude). No PII leaves your device.
  4. Local Restoration: The AI responds with placeholders, and the Aegis local server swaps them back to your real, private values.
  5. Final Output: You see the normal, helpful response with your data intact.

Support

If you need help setting up your local Aegis server, please contact support.

License

This software is provided under a proprietary license for use with the Aegis AI platform. All rights reserved.

Metadata

Release files for aegis-local 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for aegis-local 0.1.2
File Size Uploaded Provenance
aegis_local-0.1.2.tar.gz 15.0 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for aegis-local 0.1.2
File Interpreter ABI Platform
aegis_local-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 29.6 kB

Release files / aegis_local-0.1.2.tar.gz

Download URL aegis_local-0.1.2.tar.gz
Size 15.0 kB
Tags Source
SHA-256 checksum
How to use checksums
e1a77574a70dd09f55567e2b94494ea7f6bb6f86a1eda83358dc05111c5f899c
BLAKE2b-256 checksum
How to use checksums
50968734a0daac19ce9c4118f8c290da0162d95a8da5cba5fe68049344d888a7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.13

Release files / aegis_local-0.1.2-py3-none-any.whl

Download URL aegis_local-0.1.2-py3-none-any.whl
Size 14.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b086c1c0bb89c9a213657c97b09a4aa0f8a016bd6a2b09fdb5e4c92004c5ce48
BLAKE2b-256 checksum
How to use checksums
408ddd51cba0693d97dda3e43cb730c06f7b39a6f2c555a02e32136d6952c9a4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.13

Security for aegis-local 0.1.2

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A 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.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page