Skip to main content

Pick your path

There are three ways to add alignment verification and integrity checking to your AI agents. Choose the one that fits your constraints.

Smoltbot 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 smoltbot, the API, and the database on your own infrastructure. Complete data residency. Cloudflare Workers + Supabase stack.

Comparison

FeatureGatewaySDK DirectSelf-Hosted
Setup time5 minutes30 minutes2 hours
Code changesNoneModerateModerate
AAP tracesAutomaticManualAutomatic
AIP integrityAutomaticManualAutomatic
DashboardIncludedIncludedSelf-hosted
Data residencyMnemom cloudMnemom cloudYour infrastructure
Enforcement modesobserve / nudge / enforceYou implementobserve / nudge / enforce
Policy governanceCLPI built-inYou configureCLPI built-in
Multi-providerAnthropic, OpenAI, GeminiAny (you extract thinking)Anthropic, OpenAI, Gemini
CostUsage-basedUsage-basedFree (you pay infra costs)

Which Should I Choose?

Use the Smoltbot Gateway. Install the CLI, run smoltbot init, and your existing LLM 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 smoltbot stack (Cloudflare Workers + Supabase) on your own accounts. All data stays in your infrastructure. Same automatic tracing as the gateway, but you control everything.
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.