Intelligence API

Advanced Memory
& Intelligence API

Structured memory engine that categorizes, prioritizes, and evolves with your business - all in one powerful API.

Semantic Memory Engine
Vector-backed persistent memory with deduplication and retrieval scoring.
Reasoning Layer
Configurable chain-of-thought inference with structured output support.
Memory Engine Active

Intelligence Primitives

Built on five intelligence primitives.

Every capability is exposed as a clean API endpoint. Compose them independently or as a unified intelligence layer.

Memory Storage

Persistent, structured memory store for long-term context. Write once, retrieve semantically, persist across sessions.

POST /memory/write TTL support

Semantic Search

Vector-based retrieval with similarity scoring and configurable top-k results. Powered by embeddings, no infrastructure required.

POST /memory/search cosine similarity

Reasoning Engine

Chain-of-thought inference with configurable depth and structured output modes. Returns reasoning steps alongside final answers.

POST /reason JSON schema output

Context Management

Dynamic context injection, window management, and deduplication. Only relevant memory is injected — reducing token waste.

windowing dedup scoring

API Access

REST and streaming endpoints with SDK support for Python, TypeScript, and cURL. Full OpenAPI spec included.

REST + SSE OpenAPI 3.1

Developer Experience

Integrate in minutes.

One API key. Three endpoints. Ship intelligent features without managing vector databases, embedding pipelines, or reasoning infrastructure.

  • Full OpenAPI 3.1 spec — import directly into Postman or Insomnia
  • Python and TypeScript SDKs with full type definitions
  • Streaming responses via Server-Sent Events for real-time UIs
  • Usage metered per call — no minimum commitment
// Write a memory entry
const response = await fetch('https://api.bizxengine.com/v1/memory/write', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    namespace: 'user_123',
    content: 'User prefers concise responses under 100 words.',
    tags: ['preference', 'style'],
    ttl: 86400  // 24h expiry
  })
});

// { "id": "mem_9xKzA", "stored": true, "tokens": 14 }

// ← response
// Run reasoning with injected context
const answer = await fetch('https://api.bizxengine.com/v1/reason', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY'
  },
  body: JSON.stringify({
    prompt: 'Summarise the user\'s onboarding status.',
    namespace: 'user_123',
    chain_of_thought: true,
    output_schema: { type: 'text' }
  })
});

// { "steps": [...], "answer": "User completed step 2..." }

// ← response

Built With BizXEngine

What builders are powering.

From production copilots to research pipelines — the same API, composed differently.

AI Copilots

Give your product a memory layer. Copilots powered by BizXEngine remember user preferences, past decisions, and domain context across every session.

memory.write memory.search reason

RAG Pipelines

Replace fragmented vector DB setups with a single API. Store documents, query semantically, and inject relevant chunks directly into your LLM context window.

memory.write memory.search context.inject

Conversational Agents

Build agents that maintain continuity across long conversations. Context windowing and deduplication prevent drift and repetition without ballooning token costs.

context.window context.dedup

Knowledge Bases

Index internal docs, support tickets, or product specs. Expose a semantic search interface over your private knowledge — without exposing raw data.

memory.namespace memory.search

Getting Started

From zero to intelligent.

Three API calls. No infrastructure setup. No vector database provisioning.

01

Connect

Add your API key. Point to our base URL. No provisioning, no cluster management.

Authorization: Bearer ...
02

Store

Push memory entries, documents, or structured context to the engine. We handle embedding and indexing.

POST /memory/write
03

Query

Retrieve, reason, and respond with full intelligence. Stream results back to your UI in real time.

POST /reason

Pricing

Simple pricing.
No surprises.

Start free. Scale as you grow. Every plan includes full API access — per workspace, no feature gating.

Plans are per Workspace — your Business Memory Brain. Create unlimited workspaces per account.
Free Starter
$0/mo

Forever free. No credit card.

Start for free
API Keys1
Writes/mo1,000
Retrievals/mo5,000
Req/min10
Reasoning/mo100
Pro Individual
$29/mo

Billed monthly. Cancel anytime.

Get started
API Keys3
Writes/mo25,000
Retrievals/mo100,000
Req/min60
Reasoning/mo2,000
Most Popular
Max Team
$99/mo

Billed monthly. Cancel anytime.

Get started
API Keys10
Writes/mo150,000
Retrievals/mo500,000
Req/min300
Reasoning/mo15,000
Enterprise Custom
Custom

Volume pricing. Dedicated infra.

Talk to us
API KeysUnlimited
Writes/moUnlimited
Retrievals/moUnlimited
Req/minCustom
Reasoning/moUnlimited
View full pricing & comparison

Developer docs.

Everything you need to integrate, extend, and ship with the BizXEngine Intelligence API.

Open full docs →
API Reference

Full endpoint documentation — auth, memory, search, reasoning, streaming, and usage events.

SDKs & Libraries

Official Python and TypeScript SDKs with full type safety, retry logic, and streaming helpers.

Memory Schemas

Namespace design, tagging strategies, TTL configuration, and deduplication threshold guides.

Get in touch

Let's build something smart.

Whether you're exploring the API, hitting scale limits, or need an enterprise contract — we respond within one business day.

Typical response < 4 hours
Mon–Fri, 9 AM–6 PM GST (UTC+4)
Online

Send us a message

We'll get back to you within one business day.

By submitting you agree to our Privacy Policy.

Message sent!

We'll reply within one business day.