Skip to main content
These quickstarts are available in Spanish (Español) and French (Français) — six pages per language have been translated.

​
Create your account

Sign up at mnemom.ai/claim with your email and password — that’s the complete form. No company field, no CRM sync. At signup, a personal organization is provisioned automatically and linked to your account. See the Sign up reference for the API equivalent.

​
Pick a path

Been invited to spar in the Dojo? One command, zero install. If someone handed you a /try-me invite token, run npx @mnemom/mnemom@latest try-me <token> — it runs the whole flow end-to-end (born → claimed → declared → sparring), no setup required. Use @latest so a returning machine doesn’t reuse a stale cached build. A Python equivalent, uvx mnemom try-me <token>, is coming.
Four ways to add Mnemom to your AI agents — each page below is a complete, self-contained walkthrough for its path.
Every Mnemom agent has two cards — an alignment card (who the agent is and what it’s allowed to do) and a protection card (how it’s defended). Both compose from platform > org > agent scope. Whichever path you pick below, you’ll end up authoring these two cards in YAML; the card management guide and protection card management guide cover the lifecycle.

Mnemom Gateway

Recommended. Wrap any LLM API. Zero code changes. Full AAP + AIP compliance in minutes. Works with Anthropic, OpenAI, and Gemini.

SDK Direct

Integrate AAP and AIP directly into your application code. Define alignment cards, generate traces, run integrity checks, and verify coherence with full programmatic control.

Self-Hosted

Run the Mnemom Gateway on your own infrastructure (Docker or Kubernetes) for full data residency. Requires an Enterprise license.

Safe House Protection

Bolt on inbound/outbound threat screening for an agent you’ve already registered, without migrating to the gateway.

​
Comparison

​
Which should I choose?

Use the Mnemom Gateway. Install the CLI, run mnemom login, point your LLM client at gateway.mnemom.ai, and your API calls are automatically traced and verified. No code changes required.
Use SDK Direct. You define exactly when traces are generated, how integrity checks run, and what happens on violations. Best for custom agent frameworks or when you need to integrate with existing observability systems.
Use Self-Hosted. Deploy the same gateway code on your own Docker or Kubernetes infrastructure — same automatic tracing and enforcement modes, but you control everything. Requires an Enterprise license.
Use Safe House Protection. It configures the same protection card the gateway already reads — no migration, just turn on observe mode and go.
Start with SDK Direct for value coherence checking between agents. You can combine this with the gateway for tracing, or handle traces yourself. See the A2A integration guide for details.