Persistent, synthesized memory for any LLM application. Two API calls. Works with any model.
Anansi is a memory layer for AI applications. You send content to it — conversations, documents, notes, meeting transcripts — and it returns synthesized, curated context ready to inject into your LLM system prompt.
Unlike raw vector databases, Anansi runs a two-layer synthesis pass on every user's data:
This is what you inject before an LLM call — not a wall of raw chunks, but a curated profile that fits cleanly in a system prompt.
Get from zero to working memory in under 5 minutes.
Full reference for /v1/ingest, /v1/context, and /v1/memory.
Add persistent user memory to a Claude-powered chatbot.
Personalise a voice agent with Anansi memory.
Share memory across background and conversational agents.
Remember every user action to personalise future interactions.
Batch-ingest onboarding answers so the app is personalised from day one.
Connect your Notion workspace to the memory engine.
Auto-ingest transcripts from any webhook source.
Sign up at /portal/login and generate a key. Keys start with ans_.
POST /v1/ingest with a userId and content string. Chunking, embedding, and synthesis queue automatically.
Anansi distills accumulated content into static facts and dynamic context for each user.
GET /v1/context?userId=X&q=topic returns the synthesized profile. Inject into your system prompt.