The Cookbook is Synap’s examples manual. Each recipe is one complete agent — what it does, when to use it, the stack it runs on, and the code to build it. Most live in our playground; the rest are in active development and ship as the recipe drops.Documentation Index
Fetch the complete documentation index at: https://docs.maximem.ai/llms.txt
Use this file to discover all available pages before exploring further.
Try before you build. Every recipe has a Playground companion you can poke at without writing a line of code. Bring API keys to the playground if you want to fork and run.
How to read a recipe
Every page follows the same skeleton, in this order:- What you’ll build — outcome bullets, est. build time
- When to use this recipe — concrete signals so you can tell if it fits your problem
- Architecture at a glance — one diagram, no jargon
- Stack — language, framework, plugins, channel
- Build it — step-by-step with Python and TypeScript side-by-side in code tabs
- Run & verify — start it locally, see memory persistence working
- Customize / extend — links to swap channels, add plugins, change scoping
- Troubleshooting — recipe-specific gotchas
- Related — framework integrations, plugins, and concepts referenced
Status legend
Live in Playground
Reference implementation runs on synap.maximem.ai/playground. Recipe code matches.
In Development
Recipe is written and runnable. Playground demo is being built — check back soon.
Consumer Agents
User-facing assistants for end-user products. Memory is keyed per consumer; one customer_id covers the whole product.Uber — Customer Support
Live in Playground · Rider-aware support agent with refunds, lost-item reports, and human handoff.
Amazon — Shopping Assistant
Live in Playground · Catalog-grounded shopping concierge with order history and preference recall.
Support Agents
Internal-or-external support workflows with escalation, ticketing, and cross-tier handoff.Tier-1 → Tier-2 Escalation Cluster
In Development · Multi-agent cluster: T1 triage agent hands off to T2 specialist with shared memory.
WhatsApp Agents
Inbound + outbound WhatsApp Business API agents. Memory survives across sessions and human handoffs.Single-WABA Inbound + Human Handoff
In Development · One WABA number, AI takes inbound, drops to human agent on signal, picks back up cleanly.
Single-WABA Inbound + Outbound Campaign
In Development · One WABA number running scheduled outbound campaigns alongside inbound support.
Multi-WABA Same-Business Shared Memory
In Development · Multiple WABA numbers under one business, one shared customer memory pool.
Voice Agents
Real-time voice agents with sub-300ms memory injection.Voice Concierge (Pipecat + ElevenLabs)
In Development · Phone agent that recalls caller history mid-call. STT → memory inject → LLM → TTS.
B2B Agents
Outbound and inbound agents for business buyers and sellers.AI SDR
In Development · Prospecting agent: research, personalize, sequence, book — with prospect memory across touches.
Salesforce — Enterprise Sales Assistant
Live in Playground · Account-grounded sales assistant with opportunity history and CRM-aware recommendations.
Personal AI Agents
Consumer-side personal agents. Strong individual user scoping; preferences and habits are the core memory.AI Companion
Live in Playground · Conversational companion that learns preferences, communication style, and ongoing context.
AI Coach
In Development · Wellness coach with goal tracking, plan adherence memory, and session continuity.
Choosing a recipe
Quick decision guide:| If you’re building for… | Start with |
|---|---|
| End-user support in a consumer app | Uber — Customer Support |
| Product discovery / commerce | Amazon — Shopping Assistant |
| Internal helpdesk with escalation | Tier-1 → Tier-2 Escalation Cluster |
| WhatsApp-first business comms | One of the three WhatsApp recipes (handoff, campaign, multi-WABA) |
| Phone / IVR replacement | Voice Concierge |
| Outbound B2B prospecting | AI SDR |
| Enterprise sales enablement | Salesforce — Enterprise Sales Assistant |
| Consumer companion / lifestyle app | AI Companion or AI Coach |
Stack you’ll need
Every recipe runs on the Synap SDK plus one or more of:- Frameworks — see AI Integrations for the full list (LangChain, OpenAI Agents, Vercel AI SDK, Mastra, Pipecat, LiveKit, etc.)
- Plugins — see Plugins for tool extensions (OpenClaw, more coming)
- Concepts — recipes link out to the Concepts section when scoping or memory architecture matters
TypeScript prerequisite: The JavaScript SDK wraps the Python SDK as a subprocess. Every TS recipe requires Python 3.11+ on the host and pins Next.js route handlers to
export const runtime = "nodejs". Edge Runtime, Cloudflare Workers, Bun, Deno Deploy, and Lambda Node-only runtimes are not supported. See Installation → JavaScript / TypeScript SDK.