Memory

Memory is not a separate product — it's a property of a request. Add a memory field to a chat completion and the gateway retrieves relevant facts about the user before the model call and persists new ones after. Everything else you already get from Cencori — BYOK, PII redaction, audit logs, spend caps — composes for free, because memory goes through the same pipeline.

A new chat is not a memory reset. It's a fresh conversation with a model that already knows the user.

const response = await cencori.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'What did we agree about pricing?' }],
  memory: { userId: session.user.id },
});
 
console.log(response.choices[0].message.content);
console.log(response.memory?.retrieved); // facts injected into this reply

When memory is present, retrieval and writeback both default to on. Omit the field for a stateless chat.

The response carries a memory block:

{
  "choices": [ ... ],
  "memory": {
    "retrieved": [{ "id": "mem_xxx", "score": 0.82, "content": "Prefers TypeScript" }],
    "written": [],
    "write_status": "pending"
  }
}

Writeback runs asynchronously after the response, so written is empty and write_status is pending on the same request — the facts are available on the next turn. The streaming response also sets an X-Cencori-Memory-Retrieved header with the injected count.

For managing memories outside a chat — settings pages, GDPR panels, manual seeding.

// Seed a fact
await cencori.memory.write({
  userId: session.user.id,
  content: 'Prefers dark mode. Uses TypeScript primarily.',
});
 
// Search
const { results } = await cencori.memory.searchUser({
  userId: session.user.id,
  query: 'ui preferences',
  topK: 3,
});
 
// Forget
await cencori.memory.forget(results[0].id);

You don't have to route inference through Cencori to use memory. Keep your existing OpenAI / Anthropic / Bedrock / LangChain setup exactly as-is and bolt memory on beside it with two helpers:

import { Cencori } from 'cencori';
const cencori = new Cencori({ apiKey: process.env.CENCORI_API_KEY });
 
// 1. Recall — returns an inject-ready system string ('' if nothing yet)
const context = await cencori.memory.recall(userId, userMessage);
 
// 2. Your existing model call — untouched
const completion = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    ...(context ? [{ role: 'system', content: context }] : []),
    { role: 'user', content: userMessage },
  ],
});
const reply = completion.choices[0].message.content;
 
// 3. Remember — we extract the durable facts from the exchange and store them
await cencori.memory.remember(userId, { user: userMessage, assistant: reply });

remember runs the same fact extraction the gateway uses (customizable via extract), redacts before writing, and enforces org isolation and quota — all without any inference going through Cencori. recall is a thin wrapper over search that formats results the same way the gateway injects them.

Under the hood these map to POST /v1/memory/remember and POST /v1/memory/search. Embeddings use your project's OpenAI key if configured (BYOK), or Cencori's managed key otherwise — so zero provider setup is required to start.

cencori/react ships a drop-in <Chat> component. Pass memory and the conversation is stateful across sessions:

import { Chat } from 'cencori/react';
 
<Chat
  model="gpt-4o"
  apiKey={process.env.NEXT_PUBLIC_CENCORI_KEY!}
  memory={{ userId: session.user.id }}
/>

It streams by default and shows a subtle "recalled N memories" indicator so users know the model remembers them.

The useMemory hook

For custom UI — a "what we remember about you" panel with right-to-be-forgotten:

import { useMemory } from 'cencori/react';
 
function MemorySettings({ userId }: { userId: string }) {
  const { memories, forget, exportAll, loading } = useMemory({
    userId,
    apiKey: process.env.NEXT_PUBLIC_CENCORI_KEY,
  });
 
  if (loading) return <p>Loading…</p>;
 
  return (
    <div>
      <h2>What we remember about you</h2>
      {memories.map((m) => (
        <div key={m.id}>
          <span>{m.content}</span>
          <button onClick={() => forget(m.id)}>Forget</button>
        </div>
      ))}
      <button onClick={exportAll}>Download my data</button>
    </div>
  );
}

useMemory returns { memories, loading, error, refresh, write, search, forget, exportAll }.

• PII redaction runs before writeback. The raw value never persists — the gateway's PII pipeline tokenizes SSNs, redacts names, etc. on any string headed for storage.
• Hard boundary at the organization. Under no code path can a memory written by one org be read by another. Enforced in SQL and property-tested against the live database.
• Forget is real deletion. DELETE /v1/memory/:id removes the row and its embedding.
• Opt-in per request. No memory field means no memory. Nothing is stored unless you ask for it.

Memory is metered by count per project (each memory has a 10KB content soft cap). Free projects get 1,000 memories with 30-day session / 90-day user retention. At 100% the gateway returns 429 memory_quota_exceeded on writes only — reads keep working, so your product never silently forgets its users.