Fireraven Agent Hooks

Fireraven Agent Hooks

FireGuard guardrails for AI coding agents: **Windsurf/Cascade**, **Devin Local**, **Cursor**, **Claude Code**, **GitHub Copilot**, and **Microsoft Copilot Studio**.

Block secret leakage, dangerous execution, and data poisoning at the hook layer — before prompts, shell commands, MCP calls, and file writes reach your agent.

flowchart LR
    userAction["Prompt, command, MCP call, or file access"] --> agentHook["Agent hook"]
    agentHook --> localContext["Normalize event context"]
    localContext --> fireguard["FireGuard policy check"]
    fireguard --> decision{"Safe?"}
    decision -->|Yes| allowAction["Allow agent action"]
    decision -->|No| blockAction["Block with guardrail message"]

Quick install for macOS, Linux, and WSL

curl -fsSL https://raw.githubusercontent.com/fireravenai/fireraven-agent-hooks/refs/heads/main/install.sh | sh

Install all supported local agents:

curl -fsSL https://raw.githubusercontent.com/fireravenai/fireraven-agent-hooks/refs/heads/main/install.sh | sh -s -- --agent all

Install GitHub C