AEGIS AI Agent Security

Open-source desktop security for local AI agents, with skill/configuration reviews, alerts, selected-process controls and policies on configured command-line and MCP routes. Windows-first beta.

AEGIS Monitoring — source UI preview, simulated data, 11 October 2026

Cost / License

Free
Open Source (MIT)

Application type

Process Monitoring Tool

Since

Updated

Updated Nov 2026

Platforms

Windows

AEGIS Local Security — source UI preview, simulated data, 11 October 2026

Alternatives

0likes

2alternatives

0articles

Features

Process Monitoring

AEGIS AI Agent Security information

Developed by
Escape Studio
Licensing
Open Source (MIT) and Free product.
Written in
JavaScript
Alternatives
2 alternatives listed
Badge
Get an embeddable badge for AEGIS AI Agent Security
Supported Languages
- English

AlternativeTo Categories

Security & Privacy, OS & Utilities

GitHub repository

159 Stars
29 Forks
88 Open Issues
Updated Nov 6, 2026

View on GitHub

Popular alternatives

View all

AEGIS AI Agent Security was added to AlternativeTo by Escape-Studio on Oct 27, 2026 and this page was last updated Oct 27, 2026.

No comments or reviews, maybe you want to be first?

AppStores & Other Links

What is AEGIS AI Agent Security?

AEGIS is a free, MIT-licensed Windows-first desktop security application for people running local AI agents.

Choose a local folder or agent profile for static review of suspicious patterns in skills and project settings before bringing them into a workflow. Compare saved snapshots to see what changed.

Investigate detected-agent process trees, configured file activity, TCP endpoints and alerts with captured evidence. Suspend or resume a currently observed selected process, or stop it with explicit confirmation. AEGIS rechecks its identity before acting.

Explicitly configured AEGIS execution and selected-action routes enforce allow/deny policies and block policy-denied commands before they start. Separately, the validating MCP gateway requires exact one-use approval for a tool and its arguments.

The workspace also includes CPU/RAM charts, Claude Code token subtotals and estimated costs, audit history and report exports.