hardenrun/aif

On device Firewall for Coding and Personal Agents

What it solves

It provides a safety layer for local coding agents to prevent them from executing dangerous or unauthorized commands, specifically focusing on blocking secrets from leaking or being misused.

How it works

It integrates with various AI coding agents via native hooks, bridge processes, or proxies to intercept and block commands before they are executed. It includes a local dashboard for monitoring and a configuration system to manage safety rules.

Who it’s for

Developers using AI coding agents (such as Claude Code, Cursor, or Gemini CLI) who want to ensure their agents operate within safe boundaries and do not leak sensitive information.

Highlights

  • Native hooks and pre-execution blocking for tools like Claude Code, Codex, and Cursor.
  • Support for a wide range of agents including Gemini CLI, Kiro, OpenClaw, and Hermes.
  • Local dashboard for visibility into agent actions.
  • Privacy-focused telemetry that only collects anonymous operational counters.

Related

  • Project
    hashgraph-online/hol-guard

    HOL Guard is a Python‑based, local‑first antivirus for AI agents. It intercepts shell commands, file access, package installs, and plugin usage, flagging secrets, destructive actions, prompt‑injection, and supply‑chain risks. Users install via `pipx`, run a wizard to hook supported agents (Codex, Claude Code, Copilot CLI, Gemini, etc.), and manage approvals through a CLI or optional cloud dashboard. The repo also provides `plugin‑scanner` for CI security checks of AI plugins, with a ready GitHub Action.

  • Project
    PrismorSec/prismor

    Prismor is a runtime security and governance platform for AI agents that monitors and enforces policies on agent actions, tool calls, and network access to prevent security risks like prompt injection and data exfiltration.

  • Project
    duncatzat/vigils

    A local-first security control plane for AI agents that prevents secret leakage, firewalls tool calls, and maintains a tamper-evident audit ledger.

  • Project
    tophant-ai/ClawVault

    A security vault and proxy gateway that protects AI agents by detecting sensitive data leaks, blocking prompt injections, and intercepting dangerous system commands.

  • Project
    giuliastro/harness-remote

    Harness Remote is an open‑source, local‑first control plane that lets you observe, pause, resume, and hand‑off native AI coding‑agent sessions (Codex, Claude, OpenCode, etc.) across devices. It runs a small Node.js gateway on a machine with a coding‑agent CLI, then connects via desktop, web, or Android clients. All code, credentials, and session data stay on your own machines; the tool only adds a UI and coordination layer.