PROJECT-ARGUS

aaron-631/PROJECT-ARGUS
★ 1 stars Python AI/LLM Updated today
Local-first security evaluation and runtime policy gateway for AI agents, MCP servers, skills, and LLM deployments
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "project-argus": {
      "command": "uvx",
      "args": [
        "project-argus"
      ]
    }
  }
}

Or install with pip: pip install project-argus

README Excerpt

Argus is a local-first security toolkit for AI agents, MCP servers, skills, and LLM deployments. It has two gates: ```text agent/config/skills ──> static + live checks ──> report + CI decision agent traffic ────────> runtime gateway ───────> allow / block / redact / audit ``` It is useful for release reviews and real authorized security checks. It is not

Topics

ai-agentsai-securityllm-securitymcppythonsarif