Checkrd
Open Source

Infrastructure for AI Agents

Policy enforcement, kill switch, and observability for every outbound API call your agents make.

main.py
from checkrd import wrap
import httpx

client = wrap(
    httpx.Client(),
    agent_id="sales-agent",
    policy="policy.yaml",
)

# Every request is now policy-enforced
response = client.get("https://api.salesforce.com/data")

Trusted by engineers building production AI agents

Everything your agents need

A single proxy layer that handles policy, safety, and observability. One line of code to integrate.

Policy Engine

YAML-defined rules enforced at the network layer. URL patterns, method filtering, rate limits, body inspection, and time-of-day restrictions.

Kill Switch

Instantly block all outbound calls from any agent. The 3 AM safety net every engineering leader deploying agents needs.

Observability

Structured telemetry for every proxied call. Endpoint, method, status code, latency. OpenTelemetry compatible.

WASM Sandbox

233KB WebAssembly core with zero I/O access. 62 microsecond evaluation. Security is architectural, not trust-based.

Open Source

The proxy core and language wrappers are open source. No vendor lock-in. Standard HTTP proxying. pip install and go.

Ready to secure your agents?

Get started in under 5 minutes with our open-source SDK.