Vercel AI SDK + Memanto
@moorcheh-ai/memanto TypeScript SDK.
Prerequisites
- Node.js 20+
- Moorcheh API key (or an on-prem Memanto backend — see On-Prem)
aiandzodinstalled in your app (optional peer dependencies of@moorcheh-ai/memanto)
Install
ai and zod are optional peer dependencies of @moorcheh-ai/memanto — install them yourself in the host app; createMemantoTools fails fast with a clear error if they’re missing.
Quick Start
createMemantoTools returns an object with three AI SDK tools — pass it straight into tools on generateText / streamText.
Available Tools
| Tool | Backed by | Description |
|---|---|---|
recallMemory | Recall | Semantic search over stored memories. query (required), limit (1-50), type (filter by memory type). |
rememberMemory | Remember | Persist a durable fact/preference/decision/instruction. content (required), type (optional — server auto-classifies if omitted), title, tags. |
answerMemory | Generate AI Answer | RAG-synthesized answer over stored memories. question (required), limit (1-100). |
recallMemory: “Call this before answering whenever the user refers to information from earlier or from a previous session”).
Options
Memory Types
type fields are constrained to Memanto’s 13 supported types via a shared MEMORY_TYPES export:
On-Prem
The integration talks to Memanto through theMemanto client, so it works identically against an on-prem backend — no code changes, just configure the backend once with the CLI. See On-Prem Overview and the TypeScript SDK Reference.
Next Steps
- TypeScript SDK Reference for the full
Memantoclient API - Mastra Integration for the equivalent Mastra tools
- OpenAI Integration for the equivalent OpenAI
runTools()tools - Memory Types Reference