Now in Public Beta

Give your AI agent a memory
that never forgets

Tokyo Brain is the universal memory infrastructure for AI agents. Persistent, context-aware, cross-platform memory storage.

<100ms
Local embedding
50+
Languages supported
AES-256
Encryption at rest

Every AI agent has amnesia

🧠

Coding assistants forget architecture

Yesterday you decided on a microservices pattern. Today your AI suggests a monolith. Every session starts from zero.

πŸ”„

Chatbots repeat themselves

Your AI asks the same onboarding questions every time. Users notice. Trust erodes.

🌐

Context doesn't cross platforms

What your agent learns in Slack stays in Slack. Your Discord bot has no idea what happened in your IDE.

User: Use the microservices arch we discussed
AI: I don't have any context about previous discussions.
User: We talked about this yesterday...
AI: I apologize, but I don't have access to our previous conversations.
// Session memory: wiped. Again.

Three primitives. Infinite memory.

A simple REST API that gives any AI agent persistent, searchable, privacy-compliant memory.

πŸ’Ύ

Store

Save memories with full state and history tracks. Every memory is versioned β€” you can always trace how context evolved over time.

POST /store
πŸ”

Recall

Semantic search with structured format returns. Temporal metadata prevents hallucination β€” your agent knows when it learned something, not just what.

POST /recall
πŸ—‘οΈ

Forget

GDPR-compliant hard deletion. When a user says "forget me," you actually can. Cascading delete across all storage tiers.

DELETE /forget

Built different. By design.

🌍

50+ Languages

Multilingual embedding means you can search in Chinese and find results stored in Japanese. Or query in English and surface memories written in Korean. No translation layer needed.

⚑

3-Tier Architecture

Hot memories in Redis for sub-millisecond access. Warm semantic search via ChromaDB. Cold knowledge graphs in Neo4j for deep relational queries. Data flows automatically between tiers.

πŸ”Œ

Plugin-First

pip install tokyo-brain-aider β€” not another SDK to learn. We build plugins for tools you already use, not the other way around.

πŸ”’

AES-256-GCM Encryption

Every memory is encrypted at rest with AES-256-GCM. L0 privacy layer strips PII before storage. L1 layer adds per-tenant key isolation. Your users' data stays yours.

Three lines to persistent memory

No boilerplate. No config files. No SDK initialization ceremony. Just import, connect, and remember.

  • βœ“ Async-native Python client
  • βœ“ Automatic embedding β€” just send text
  • βœ“ Structured recall with temporal context
  • βœ“ Full CRUD with cascading forget
memory.py
from tokyo_brain import Brain

brain = Brain("your-api-key")

# Store a memory
brain.store(
    content="User prefers microservices architecture",
    agent="coding-assistant",
    user="user_123"
)

# Recall memories
results = brain.recall(
    query="architecture preferences",
    user="user_123",
    limit=5
)

# GDPR: forget a user
brain.forget(user="user_123")

Start free. Scale when ready.

No credit card required. Upgrade or downgrade anytime.

Free
$0
Perfect for prototyping
  • 1,000 memories
  • 500 recalls / month
  • 1 agent
  • Community support
Get Started
Fleet
$49/mo
For teams at scale
  • Unlimited memories
  • Unlimited recalls
  • Unlimited agents
  • Dedicated support
  • L0 + L1 privacy layers
  • Custom retention policies
Contact Sales

vs the competition

Feature Tokyo Brain Mem0 Zep
Plugin model (works inside your tools) βœ“ βœ— βœ—
50+ language embedding & search βœ“ βœ— βœ—
L0/L1 privacy layers βœ“ βœ— βœ—
Zero marginal embedding cost βœ“ βœ— βœ—
Sub-100ms local embedding βœ“ βœ— βœ—

Ready to give your agents
permanent memory?

Join hundreds of developers building AI agents that actually remember.

Get your API key

Start building AI agents with persistent memory in under 5 minutes.

2,847 developers joined
βœ…

You're in!

Click to copy

We'll email you setup instructions and docs access.
Welcome to Tokyo Brain πŸ§