gendigitalinc/sage
180 stars · Last commit 2026-04-09
Lightweight Agent Detection & Response (ADR) layer for AI agents — guards commands, files, and web requests. Part of Gen Agent Trust Hub.
README preview
# Sage **Safety for Agents** - a lightweight Agent Detection & Response (ADR) layer for AI agents that guards commands, files, and web requests. <p align="center"> <img src="images/sage-logo-shaded.png" alt="Sage" width="50%"> </p> Sage intercepts tool calls (Bash commands, URL fetches, file writes) via hook systems in [Claude Code](docs/platform-guides/claude-code.md), [Cursor / VS Code](docs/platform-guides/cursor.md), [OpenClaw](docs/platform-guides/openclaw.md), and [OpenCode](docs/platform-guides/opencode.md), and checks them against: - **URL reputation** - cloud-based malware, phishing, and scam detection - **Local heuristics** - YAML-based threat definitions for dangerous patterns - **Package supply-chain checks** - registry existence, file reputation, and age analysis for npm/PyPI packages - **Plugin scanning** - scans other installed plugins for threats at session start ## Quick Start ### Claude Code Requires [Node.js >= 18](https://nodejs.org/).