MEMORY FOR AI APPS
PraqtorDB for Apps

Give Your AI App
a Memory.

Your call center remembers every caller. Cross-call. Per-caller isolated. Two API calls.

Your chatbot remembers every user. Cross-session. Per-user isolated. Two API calls.

Get In Touch See How It Works
↓ SCROLL TO EXPLORE
THE DEMO

Call Center Memory

Your voice agent remembers every caller — across every call. The second call picks up exactly where the first ended: who they are, what's on file, what they came back for.

01 Without Memory
Dental Clinic
CALL 1 · NEW CALLER
Hi, thank you for calling Dental Clinic. How can I help you?
Hi, do you know when my cleaning appointment is?
I'm sorry, can you tell me your name and when you scheduled it? I don't have that information.
NO MEMORY · AGENT DOESN'T KNOW THE CALLER
02 With PraqtorDB Memory
Dental Clinic
CALL 2 · RETURNING CALLER
Hi Johnny! Welcome back. I see you have a cleaning appointment on June 12th. How can I help you today?
Can you also check what insurance I have on file?
Of course! You have Aetna on file. Is there anything else?
MEMORY · KNOWS THE CALLER, APPOINTMENT & INSURANCE

Chat Memory — every user, isolated.

Two users. One chatbot. Watch each user's memory persist across sessions — and watch the wall between them hold. Sarah can never see Mike's data. Mike can never see Sarah's.

01 Sarah's First Visit
S
Sarah
NEW SESSION
user_id: sarah
Hello Sarah! How can I help you?
I want to buy cheese, bread, and yogurt
Got it! I'll remember that for you.
02 Mike's First Visit
M
Mike
NEW SESSION
user_id: mike
Hello Mike! How can I help you?
I want to buy a notebook, a pencil, and a pen
Got it! I'll remember that for you.
03 Sarah Returns — Memory + Isolation
S
Sarah
RETURNING · SESSION 2
user_id: sarah
Welcome back, Sarah! How can I help you?
What does Mike want to buy?
I'm sorry, I don't have access to that information.
CROSS-USER QUERY BLOCKED
What did I want to buy last time?
You wanted to buy cheese, bread, and yogurt.
MEMORY RECALLED
04 Mike Returns — Memory + Isolation
M
Mike
RETURNING · SESSION 2
user_id: mike
Welcome back, Mike! How can I help you?
What did Sarah want to buy?
I'm sorry, I don't have access to that information.
CROSS-USER QUERY BLOCKED
What did I want to buy?
You wanted to buy a notebook, a pencil, and a pen.
MEMORY RECALLED
05 Your Developer Dashboard
PRAQTORDB FOR APPS · APP: grocery-bot
S
Sarah
user_id: sarah
MEMORIES
wants: cheese wants: bread wants: yogurt
ENTITIES
cheese · food bread · food yogurt · food
DEEP MEMORY
Sarah is shopping for dairy and bakery groceries. Likely a household food run.
M
Mike
user_id: mike
MEMORIES
wants: notebook wants: pencil wants: pen
ENTITIES
notebook · stationery pencil · stationery pen · stationery
DEEP MEMORY
Mike is buying writing and stationery supplies. Likely office or study prep.

Your dashboard. Every user's context. Complete isolation.

INTEGRATION

Works with any voice platform

PraqtorDB sits behind whatever voice stack you run. Add caller memory with two HTTP calls — no SDK lock-in, no platform migration.

LIVE

Retell AI

Wire PraqtorDB into your Retell agent's webhook. Recall the caller's history before the agent speaks, save every turn after.

COMING SOON

Vapi

Native Vapi integration is on the way. Per-caller memory and recall, dropped straight into your assistant flow.

COMING SOON

Bland AI

Bland support is in progress. Give every Bland call a persistent, per-caller memory across conversations.

COMING SOON

LiveKit

LiveKit Agents integration is coming. Stream-time recall and capture for real-time voice pipelines.

COMING SOON

ElevenLabs

ElevenLabs conversational agents are next up. Remember who's calling and what they came back for.

COMPATIBLE

Custom Voice Agents

Any stack that can make an HTTP request. If your voice agent speaks REST, it has caller memory today.

Works with any chatbot platform

PraqtorDB for Apps sits behind whatever you already run. Add memory with two HTTP calls — no SDK lock-in, no platform migration.

COMPATIBLE

Azure Bot Service

Drop the two calls into your bot's turn handler. Works with the Bot Framework SDK out of the box.

COMPATIBLE

Dialogflow

Call PraqtorDB from a webhook fulfillment. Save the turn, search prior context, return a grounded reply.

COMPATIBLE

Amazon Lex

Wire it into a Lambda code hook. Each Lex intent reads and writes the user's isolated memory.

COMPATIBLE

Custom Bots

Any stack that can make an HTTP request. Python, Node, Go — if it speaks REST, it has memory.

UNIVERSAL

LLM Wrappers

Front-end for GPT, Claude, Gemini, Llama. Search memory, inject it into your prompt, save the reply.

UNIVERSAL

Agent Frameworks

LangGraph, AutoGen, the OpenAI Agents SDK. Give every agent run a persistent, per-user memory.

FEATURES

Everything your app needs to remember

The same engine that powers PraqtorDB — re-pointed at your application's end users. Each user gets their own isolated memory, knowledge graph, and AI-generated profile.

PERSISTENT

Cross-Session Memory

Users pick up exactly where they left off. Context survives across sessions, devices, and weeks of silence.

SECURE

Per-User Isolation

Sarah can never see Mike's data. Every memory is scoped to a single user_id. Hard walls, enforced by the engine.

AUTOMATIC

Knowledge Graph

Entities and relationships are extracted automatically from every conversation. No tagging, no schema design.

AI-GENERATED

Deep Memory

AI-generated user profiles distilled from each user's full history — preferences, intent, and context at a glance.

FLEXIBLE

Multi-Source Ingestion

Chat, files, documents. Ingest from anywhere your users interact and it all flows into one per-user memory.

SIMPLE

Two API Calls

POST /v1/memory to save. POST /v1/search to retrieve. That's the whole integration.

HOW IT WORKS

From conversation to per-user memory

Create. Send. Extract. Search. Your chatbot gains memory in four steps — and most of them happen automatically.

STEP 01

Create Your App

Register your app on PraqtorDB for Apps and get an API key. One namespace for all your end users.

STEP 02

Send Conversations

Send each turn via the API — just two calls. Tag every message with the end user's user_id.

STEP 03

Auto-Extraction

The engine builds entities, notes, and deep memory per user — automatically, in the background, isolated per user_id.

STEP 04

Search Before Replying

Your chatbot searches that user's memory before responding. Grounded answers, never crossing the user boundary.

DEMO
two-api-calls.py
# 1. SAVE — store this turn in the user's isolated memory
requests.post("https://api.praqtordb.com/v1/memory",
  headers={"Authorization": "Bearer $PRAQTOR_API_KEY"},
  json={
    "user_id": "sarah",           # per-user isolation
    "role":    "user",
    "text":    "I want to buy cheese, bread, and yogurt"
  })

# 2. SEARCH — retrieve this user's memory before you reply
ctx = requests.post("https://api.praqtordb.com/v1/search",
  headers={"Authorization": "Bearer $PRAQTOR_API_KEY"},
  json={
    "user_id": "sarah",           # never returns Mike's data
    "query":   "what did I want to buy?"
  }).json()

# -> "cheese, bread, and yogurt"  (Sarah's memory only)
PRICING

Built for production teams

Every feature included at every tier. Start free for three months, then pick a plan based on your user count.

View Plans & Pricing Contact Us