# AgentGuard, hosted for you.

Product / AgentGuard SaaS

Early access

We run the platform. You connect your agent with our SDK and see its runs, controls and evidence in one place.

## Create your account.

Sign up with your work email and confirm it with the code we send you.

[Create your account](https://ag-dev.actaclad.com/auth/sign-up)

[Sign in](https://ag-dev.actaclad.com/auth/sign-in)


## Connect your agent.

JavaScript and Python SDKs are available.

Create a project, copy its keys and add the SDK.

JavaScript: npm install @actaclad/agentguard

Python: pip install actaclad-agentguard


## See your first run.

Run your agent. Each run shows up in AgentGuard with its model calls, tool calls and control decisions.


## One agent. Every decision, connected.

AgentGuard captures each agent run as a trace: model calls, tool calls, latency and token usage.

AgentGuard guardrails detect and redact sensitive data such as PII, secrets and tokens in prompts and outputs.

AgentGuard tool_permission sets each tool an agent can call to ALLOW, READ_ONLY, APPROVAL_REQUIRED or BLOCK, with a per-tool call cap.

AgentGuard checks model responses with output guardrails such as schema validation, hallucination and toxic-content checks.

Custom policies apply keyword or regex rules to inputs and outputs, scoped to selected agents.

AgentGuard records each control decision as evidence.


## Good to know.

Need AgentGuard in your own cloud or on your own VMs, or a security review before you start? Talk to ActaClad.

[Talk to ActaClad](https://www.actaclad.com/contact)


[Contact ActaClad](https://www.actaclad.com/contact)
