Anansi Docs — Memory API for AI apps

Personalise a voice agent

Give your voice agent persistent memory of each caller — names, preferences, past calls — with sub-30ms retrieval on warm cache.

Warning

Latency is everything in voice. A 200ms delay before TTS is audible. The patterns below keep Anansi off your critical path.

Architecture

Call connects → pre-warm memory

Immediately fetch GET /v1/context?userId=callerId (no query). This primes the Redis cache so the first-turn retrieval is instant.

User speaks → STT + memory in parallel

Start transcription and fetch /v1/context?userId=callerId&q=transcript concurrently. Both finish around the same time.

Build system prompt → LLM → TTS

Inject the memory profile. Generate response with Claude. Feed to ElevenLabs or OpenAI TTS.

Ingest the turn (background)

Fire-and-forget POST /v1/ingest after TTS starts — never on the critical path.

Pre-warm at session start

When the call connects, before the user says anything, kick off a context fetch with no query. This loads the synthesized profile into Redis cache (TTL 60s) so every turn in the call hits the fast path.

typescriptvoice-session.ts
"kw">const ANANSI_URL = "https:">class="cm">//anansimemory.com";
"kw">const ANANSI_KEY = process.env.ANANSI_API_KEY!;

"kw">class="cm">// Call this the moment the phone call connects
"kw">export "kw">async "kw">function onCallStart(callerId: "kw">string) {
  "kw">class="cm">// Pre-warm: fetches profile into cache, ~80ms on first call, ~15ms after
  "kw">const profile = "kw">await fetch(
    `${ANANSI_URL}/v1/context?userId=${encodeURIComponent(callerId)}`,
    { headers: { Authorization: `Bearer ${ANANSI_KEY}` } }
  ).then((r) => r.json());

  "kw">const isReturning = profile.static.length > 0;
  "kw">return { profile, isReturning };
}

Per-turn implementation

typescriptvoice-turn.ts
"kw">import Anthropic "kw">from "@anthropic-ai/sdk";

"kw">const anthropic = "kw">new Anthropic();

"kw">export "kw">async "kw">function handleVoiceTurn(
  callerId: "kw">string,
  transcript: "kw">string,                              "kw">class="cm">// "kw">from STT
  history: { role: "user" | "assistant"; content: "kw">string }[],
  sessionId: "kw">string
) {
  "kw">class="cm">// Fetch memory with the transcript as query — concurrent with "kw">any post-STT work
  "kw">const memory = "kw">await fetch(
    `${ANANSI_URL}/v1/context?userId=${encodeURIComponent(callerId)}&q=${encodeURIComponent(transcript)}`,
    { headers: { Authorization: `Bearer ${ANANSI_KEY}` } }
  ).then((r) => r.json());

  "kw">const isReturning = memory.static.length > 0;
  "kw">const system = [
    isReturning
      ? `You remember this caller. Their name may appear in the facts below.`
      : `You are a friendly voice assistant. This is a "kw">new caller.`,
    "Keep every response under 2 sentences. Natural, conversational tone.",
    ...memory.static.map((f: "kw">string) => `Fact: ${f}`),
    ...memory.dynamic.map((d: "kw">string) => `Recent: ${d}`),
  ].join("\n");

  "kw">const response = "kw">await anthropic.messages.create({
    model: "claude-haiku-4-5-20251001",
    system,
    messages: [...history, { role: "user", content: transcript }],
    max_tokens: 100,   "kw">class="cm">// short replies = faster TTS
  });

  "kw">const reply = response.content[0]."kw">type === "text" ? response.content[0].text : "";

  "kw">class="cm">// Ingest after TTS starts — zero impact on latency
  fetch(`${ANANSI_URL}/v1/ingest`, {
    method: "POST",
    headers: { Authorization: `Bearer ${ANANSI_KEY}`, "Content-Type": "application/json" },
    body: JSON.stringify({
      userId: callerId,
      content: `Caller: ${transcript}\nAgent: ${reply}`,
      sourceType: "voice",
      sessionId,
    }),
  }).catch(() => {});

  "kw">return reply;
}

Latency targets

Operation	Warm cache	Cold cache
`GET /v1/context` (no query)	~15ms	~80ms
`GET /v1/context` (with query)	~30ms	~150ms
Claude Haiku (100 tokens)	~300ms	~300ms
ElevenLabs streaming TTS	~200ms first audio	~200ms first audio

Pre-warming at call start means every per-turn fetch hits the warm path. Total time-to-first-audio stays under 600ms.

Caller identification strategies

Phone number (+14155551234) — always available via Twilio or Vonage. Best for anonymous callers who call back.
Account ID — if callers enter a PIN to authenticate before the agent starts, use their account ID as userId.
Email / username — for authenticated web-based voice interfaces (browser microphone).