@mubit-ai/ai-sdk

Vercel AI SDK middleware backed by MuBit memory engine.

Wraps any AI SDK model with automatic memory injection and interaction capture.

Install

npm install @mubit-ai/ai-sdk

Usage

import { wrapLanguageModel } from "ai";
import { mubitMemoryMiddleware } from "@mubit-ai/ai-sdk";

const model = wrapLanguageModel({
  model: openai("gpt-4o"),
  middleware: mubitMemoryMiddleware({
    apiKey: "mbt_...",
    sessionId: "session-1",
  }),
});

// All generateText/streamText calls through this model
// automatically get lessons injected + interactions captured
const { text } = await generateText({ model, prompt: "Hello" });

How it works

The middleware has two hooks:

1. transformParams — Before each LLM call, fetches relevant lessons from MuBit and injects them into the system prompt
2. wrapGenerate — After each LLM call, captures the interaction and ingests it to MuBit (fire-and-forget)

Options

| Option | Default | Description | | --- | --- | --- | | apiKey | MUBIT_API_KEY | MuBit API key | | endpoint | MUBIT_ENDPOINT / http://127.0.0.1:3000 | MuBit endpoint URL | | sessionId | "default" | Session/run ID for scoping memory | | userId | "" | User ID for scoping memory | | agentId | "ai-sdk" | Agent ID for attribution | | maxTokenBudget | 2048 | Token budget for context retrieval | | entryTypes | server default | Memory entry types to retrieve | | sections | server default | Context sections to include | | injectLessons | true | Whether to inject lessons before calls | | captureInteractions | true | Whether to capture interactions after calls | | failOpen | true | Proceed without lessons on error | | mubitClient | auto-created | Pre-configured MuBit client |

Features

• TTL-bounded in-memory cache (30s, 100 entries) for context retrieval
• Fail-open by default — LLM calls proceed even if MuBit is unreachable
• Fire-and-forget ingestion — doesn't block on capture
• Compatible with generateText, streamText, and any AI SDK model

Development

node --test test/**/*.test.js

License

Apache-2.0