Persistent memory for AI apps
Store any text, search it in natural language, and feed the results back into your prompts, so your users never repeat themselves.
Your LLM forgets everything between sessions, so your users do the repeating, and churn. Smritea is the persistent memory layer that remembers for them: store any text, recall it in plain language, feed it back into your prompt.
Stateless AI has a memory problem, and your users feel it.
Every session starts from zero: users re-explain themselves, agents lose the thread, assistants forget what they were told yesterday. What that costs you, measured:
walk away the first time a bot makes them repeat themselves; 60% won't repeat twice.
Parloa survey, 1,001 consumers: cfodive.comexpect the assistant to already know who they are and their history.
Salesforce, via Sinch: sinch.comIt is not just the support bots. Every stateless LLM app (agents, assistants, copilots) begins each session with no idea who it's talking to.
One memory layer. Every agent.
Support, sales, assistants, copilots, internal knowledge, vertical agents: the same add() / search() memory, wherever your users are.
Customer support
Remembers the customer across call, WhatsApp and email, so they never repeat themselves.
Sales & SDR
Recalls every prospect touch, objection and next step across the deal.
Personal assistant
Knows preferences and context across sessions, so it stops re-asking.
Coding copilot
Holds project context, conventions and past decisions.
Internal knowledge
Answers across docs, Slack and tickets, with sources.
Vertical agents
Remembers a patient, client or case across every visit.
Every fact your users share, remembered across sessions, across months, searchable the moment you need it back.
A memory layer your app queries in plain language.
One add() to remember, one search() to recall, with per-user scope, a knowledge graph, and time-aware retrieval underneath.
Per-user memory
Every memory belongs to an actor inside your app, so search returns only that user's context. No leakage.
Graph-linked recall
Entities are extracted and connected automatically; deep_search walks the graph to surface related facts in ~700ms (measured).
Time-aware
Memories carry lifecycle and temporal fields, so you can recall the world as it stood on any date.
It's two calls.
Install the SDK, add a memory, search it back. Full walkthrough on the examples page.
# pip install smritea-sdk
client.add("User prefers dark mode",
scope=MemoryScope(actor_id="user-123", actor_type="user"))
hits = client.search("What UI does the user prefer?",
speaker_actor_id="assistant-1", # who's asking — speaker-aware, never a filter
scope=MemoryScope(actor_id="user-123", actor_type="user"))
Meet Smonku
Every conversation your users have, every preference they share, every detail that matters: Smonku keeps it all. He sits at his desk, organizes memories into glowing orbs, and hands them back when your app needs them.
Give your app a memory.
Free tier included. Create an account and store your first memory in minutes.
Get your API keyPlans that grow with you
Simple, transparent pricing for every stage, from your first prototype to a production fleet.