jimmyracheta/AI-Runtime-Guard

> Your agent can say anything. It can only do what policy allows.
AI agents with filesystem and shell access can delete files, leak credentials, or execute destructive commands, often without the user realizing until it is too late.
**Runtime Guard** sits between your AI agent and your system, enforcing policy on every file and shell action before it executes. Install once, configure your rules, and your agent operates within the boundaries you set. Works with Claude Code, Claude Desktop, Cursor, Codex, and any MCP-compatible client. No retraining, no prompt engineering, no external account required.
See it in action
Quick start
After setup, open http://127.0.0.1:5001 and add your first agent from Settings -> Agents.
Alternative install methods (venv, source, CI)
Alternative quick start (venv):
1. python3 -m venv .venv-airg && source .venv-airg/bin/activate
2. python -m pip install --upgrade pip
3. python -m pip install ai-runtime-guard
4. airg-setup (guided, recommended: select/create workspace during setup; includes telemetry opt-in prompt, default Yes)
5. airg-doctor
6. Open GUI Settings -> Agents, add agents manually, and apply MCP config/hardening from there.
Source-clone path:
1. git clone --branch main https://github.com/runtimeguard/runtime-guard.git
2. cd runtime-guard
3. python3 -m venv .venv-airg && source .venv-airg/bin/activate
4. python -m pip install --upgrade pip
5. python -m pip install .
6. airg-setup
7. airg-doctor
Unattended automation-only setup (CI/non-interactive):
1. airg-setup --defaults --yes --workspace /absolute/path/to/workspace
See docs/INSTALL.md for the full install reference.
What it does
**Prevention**
- Blocks destructive commands (rm -rf, privilege escalation, sensitive file access) before they run
- Auto-backs up any file before destructive or overwrite operations
**Control**
- Gates risky commands behind explicit human approval via local GUI or API
- Enforces workspace and path boundaries keyed to AIRG_WORKSPACE
- Supports per-agent policy overlays keyed to AIRG_AGENT_ID
- Configurable network policy with allowlists, denylists, and monitor/enforce modes
**Visibility**
- Logs every allowed, blocked, and pending action to activity.log
- Indexes events into reports.db for a dashboard view of agent behavior
**Hardening**
- Script Sentinel: detects attempts to launder blocked commands through scripts
- Universal agent hardening: GUI-driven posture enforcement including hooks, sandboxing, and native tool restrictions (support varies by client)
Why MCP
Runtime Guard is built as an MCP server because MCP provides the interception point you need. When your agent issues a tool call, Runtime Guard evaluates it against policy before execution. For clients that support pre-tool hooks (like Claude Code), AIRG can also deny the agent's native file and shell tools, forcing risky operations through the policy layer.
This approach is the closest to kernel-level enforcement without requiring system privileges or modifying your agent, and it works across any MCP-compatible client without per-agent engineering.
Who it is for
Developers and operators running AI agents who want deterministic guardrails on what an agent can actually do to their system, without giving up agent autonomy or rewriting their workflow.