# 🪖 OpenLegion

> Security-first AI agent framework for production multi-agent systems

Canonical HTML: https://shelldex.com/projects/openlegion/
JSON: https://shelldex.com/api/projects/openlegion.json

## Overview

Production-grade multi-agent platform built on the assumption that agents can be compromised. Every agent runs in its own Docker container with blast-radius containment through isolation, credential separation, permissions, and cost controls. Credentials live in a vault/proxy layer so agents never directly access raw keys. Includes a built-in stealth browser for human-like web interaction without fragile external browser setups. Designed for teams deploying agents in production, especially in security-sensitive or enterprise environments.

**Highlight:** Security-first agent fleet — blast-radius containment per agent, vault-proxied credentials agents never see, built-in stealth browser, per-agent budget caps

## Metadata

- GitHub: https://github.com/openlegion-ai/openlegion
- Language: python
- Status: active
- Ecosystem role: alternative
- Categories: multi-agent, security, self-hosted, enterprise, browser
- Platforms: server, messaging
- MCP support: yes
- Requires external LLM: yes
- Added to registry: 2026-03-07

## GitHub data

- Stars: 92 (92)
- Forks: 18
- Open issues: 5
- License: NOASSERTION
- Last commit: 2026-05-15T11:33:20Z
- Star growth (7d): +1

## Registry position

- Leaderboard rank: #46
- Health score: 50/100
- Days since last commit: 0