Terminal AI agents read your entire codebase for context — including .env files, database
configs, and API keys — then ship it all to remote LLMs.
Guardian is the local firewall that intercepts every prompt before it leaves your machine.
You give them access to your terminal and codebase. They read files to gain context. But they don't know the difference between a config file and a state secret.
When you ask an agent to "fix the database connection", it reads your config files,
including .env. It then packages that entire context into a massive prompt and sends it to a
remote LLM provider.
Your production database credentials, API keys, and customer PII just left your
machine. You have zero visibility into what was sent.
What if you had a local firewall sitting between your agent and the
cloud?
Guardian Runtime intercepts HTTP requests from your agent on your local machine. It scans the
prompt payload for secrets and PII using fast regex — no ML models required. If it's clean, it forwards it.
If it contains a secret, it blocks the request instantly.
Guardian runs as a local HTTP server that mimics the APIs of popular LLM providers. Point your agent's base URL to localhost. The agent never knows the difference.
Cursor, Copilot, etc.
localhost:8080
OpenAI, Anthropic, Gemini
No Docker. No complex config. Just pip install and one environment variable.
Four layers of protection that work together silently in the background.
Detects OpenAI, Anthropic, AWS, Stripe, Razorpay, GitHub keys and more. Also blocks PII like Aadhaar, PAN, SSNs, credit cards, emails, and phone numbers before they leave your machine.
Prevent agents from burning your budget in infinite loops. Set token limits per request, daily spend budgets, and per-session cost caps.
Run guardian logs to see what your agent is sending in real-time. All logs
stored locally at ~/.guardian/logs/. Zero telemetry sent to our servers.
Automatically compress agent prompts by stripping whitespace, deduplicating system messages, and trimming unnecessary chat history. Typical savings: 20–60%.