Persistent memory, personality, and context for AI agents — whether you're building an assistant, a character, or an enterprise workflow agent.

Sonzai is the Mind Layer for AI agents: a hosted platform that gives any agent persistent memory, evolving personality, mood, relationships, and a knowledge graph. Integrate via REST, MCP, or native SDKs for TypeScript, Python, and Go.

Install

Pick the path that matches your stack. All paths talk to the same hosted API — mix and match freely (e.g. backend in Python, plus MCP from Claude Desktop for ops).

pip install sonzai

Python 3.11+. Sync (Sonzai) and async (AsyncSonzai) clients ship in the same package.
TypeScript runs on Node.js >=18, Bun, and Deno. Zero runtime dependencies.
Go 1.25+. Standard library only.
All SDKs read SONZAI_API_KEY from the environment by default.
OpenClaw itself is required for the OpenClaw path — install it from openclaw.ai (Getting Started).
Full guides: MCP · OpenClaw · REST API Reference.

Need an API key first? Create a project at platform.sonz.ai, then jump to the Quickstart for the full walkthrough.

What are you building?

Pick the track that matches your product. Each quickstart walks through the features that matter for your use case — and explicitly flags what you can skip.

AI Employees & Personal AI

Task-oriented agents that remember users across sessions.

Per-user memory, custom tools, knowledge base, task notifications. Skip mood and emotions if you don't need them.

Start here →

AI Companions

Character-driven agents with personality, mood, and evolving relationships.

Big Five personality, 4D mood, relationship tracking, proactive wakeups, voice. Everything Sonzai is known for.

Start here →

Enterprise AI Agents

Workflow-aware agents for CRM, support, internal tools, and compliance.

Multi-instance isolation, webhooks, project-scoped knowledge base, custom states, eval runs.

Start here →

Core Capabilities

Every feature below works for all three audiences, but the emphasis differs. Use the In practice tabs on each page to jump to examples for your use case.

Memory & Context

Persistent memory across sessions — facts, events, commitments, and summaries. Seed, search, and browse via SDK.

All audiences

Personality

Big Five (OCEAN) model with behavioral dimensions, interaction preferences, and trait evolution.

All audiences

Emotions & Mood

Four mood dimensions that shift with conversations and events.

Best for Companions · safe to ignore for task agents

Conversations

Real-time streaming chat. Memory, mood, and personality update automatically after each turn.

All audiences

Knowledge Base

Upload documents or push structured data to build a knowledge graph agents search during chat.

All audiences

Custom Tools

Register tools the LLM can invoke during chat — built-in capabilities, persistent agent tools, and ephemeral session tools.

All audiences

Multi-Instance

One agent, many isolated contexts — per-user, per-workspace, per-environment.

Best for Employees & Enterprise

Webhooks & Notifications

Real-time event callbacks and proactive agent messages.

Best for Enterprise

Proactive Wakeups

Agents schedule check-ins based on relationship context, tasks, or SLA.

All audiences

Voice

Text-to-speech, speech-to-text, and real-time duplex voice streaming.

Best for Companions & Enterprise support

Agent Generation

Create agents from natural-language descriptions. Auto-generate personality, bio, and seed memories.

All audiences

Evaluation

Score agent quality with rubrics, run multi-turn simulations, benchmark consistency.

All audiences

How Agents Improve Over Time

The complete picture of automatic learning: memory decay, consolidation, dedup, retrieval policy learning, personality drift, breakthroughs, and the shadow-rollout system.

All audiences

BYOK — Bring Your Own Key

Run on Sonzai's stack but bill provider tokens to your own OpenAI / Gemini / xAI / OpenRouter account. Per-project, encrypted at rest.

All audiences

Integration

Quickstart

Create a project, get an API key, spin up an agent, and start chatting in under 10 minutes.

Architecture

How the platform, orchestrator, and your backend fit together.

Integration Guide

End-to-end SDK integration for TypeScript, Python, and Go.

API Reference

Full REST API reference with every endpoint and schema.

MCP Integration

Connect Claude Desktop, Cursor, or any MCP-compatible client to Sonzai.

OpenClaw Plugin

Drop-in plugin for the OpenClaw context engine.

For AI Agents

Feeding Sonzai docs to an AI assistant? Every page has a Copy for LLM button, and the bundles below are pre-formatted for ingestion.

llms.txt

Terse index of the docs for LLM tools.

llms-full.txt

Full docs concatenated for LLM ingestion.

llms-companions.txt

Subset for AI Companion builders.

llms-employees.txt

Subset for AI Employee / Personal AI builders.

llms-enterprise.txt

Subset for Enterprise Agent builders.

Each page also has a raw-markdown URL: append .md to any doc path. For example, /docs/en/memory.md returns plain markdown ready to paste into an LLM or pipe into a tool.

How It Fits Into Your Application

Your backend handles business logic and user sessions. The Mind Layer owns agent intelligence — personality, memory, mood, and relationships. Connect via REST, MCP, or SDK; pass application context per request; let the platform manage everything else.

Read the full integration guide →

Sonzai Mind Layer

Install

What are you building?

Core Capabilities

Integration

For AI Agents

How It Fits Into Your Application

On this page