內建自動過濾機制 (Sanitizer)，為你的 AI 打造零雜訊的企業級大腦。加密、多語言、持久記憶 — 你的代理只記住該記住的。
The Anatomy of a Synthetic Thought
AI Memory (Chinese)
The Transparent Self-Audit
昨天您決定採用微服務架構，今天 AI 卻建議使用單體架構。每次對話都從零開始。
您的 AI 每次都問一樣的入門問題。使用者注意到了，信任逐漸瓦解。
代理在 Slack 學到的只留在 Slack。您的 Discord 機器人完全不知道 IDE 中發生了什麼。
按 token 計費的模式下，每次遺忘的情境都是真金白銀。Tokyo Brain 將記憶儲存在外部，讓代理只檢索所需內容 — 而非完整對話歷史。
Every tenant's AI dreams. Every 30 minutes, our Default Mode Network replays memories, finds patterns, and generates insights — just like the human brain during rest. No prompts needed.
DMN insights are automatically injected into every /recall response as a "mood color." Your AI has a cognitive undertone shaped by its own overnight reflections.
Memories decay with a 60-day half-life — just like the human brain. But family names, milestones, and "I love you" are exempt forever. Your AI forgets the noise, keeps what matters.
Every night at 3AM, three AI personas (Observer, Advocate, Guardian) debate your memories in an adversarial tribunal. They find contradictions, stale beliefs, and knowledge gaps — then fix them.
10-layer recall pipeline with posterior re-ranking. Similarity, salience, confidence, trust, recency, and axiom alignment — all weighted to surface the most relevant memory first.
Bring your own LLM key (OpenAI, Anthropic, Gemini). Tokyo Brain auto-injects relevant memories into the conversation. Your AI key, our memory. POST /v1/chat
Night systems (DMN, cleaning, debate tribunal) run on YOUR API key, not ours. Full cost transparency. Set it once via POST /api/settings and your brain starts dreaming tonight.
Every API key gets its own memory space, its own dreams, its own forgetting curve. Tenant A cannot see Tenant B. Physically isolated at the collection level. Your memories are yours alone.
一個簡單的 REST API，為任何 AI 代理提供持久、可搜尋、符合隱私規範的記憶。
儲存完整狀態與歷史軌跡的記憶。每條記憶都有版本控制 — 您可以追蹤情境如何隨時間演變。
POST /store結構化格式的語意搜尋。時序元資料防止幻覺 — 您的代理不僅知道「什麼」，還知道「何時」學到的。
POST /recall符合 GDPR 的硬刪除。當用戶說「忘記我」，您真的可以做到。跨所有儲存層的級聯刪除。
DELETE /forget多語言嵌入意味著您可以用中文搜尋並找到以日文儲存的結果。或用英文查詢並檢索韓文記憶。不需要翻譯層。
熱記憶存放在 Redis 中，實現亞毫秒級存取。溫記憶透過 ChromaDB 進行語意搜尋。冷知識圖譜存於 Neo4j，支援深度關聯查詢。資料在各層之間自動流動。
pip install tokyo-brain-aider — 不是又一個要學的 SDK。我們為您已在使用的工具建構外掛，而非反過來。
每條記憶都以 AES-256-GCM 靜態加密。L0 隱私層在儲存前移除個人識別資訊。L1 層新增租戶級金鑰隔離。用戶的資料只屬於您。
在單一記憶中儲存文字、音訊特徵和視覺上下文。您的 AI 現在能看也能聽。
每條記憶都附帶 SHA-256 雜湊和數位簽章。防篡改的審計軌跡。
即插即用支援 LangChain、CrewAI、AutoGen 和 LlamaIndex。只需兩行程式碼替換。
守護者（保護情感連結）、同理心覆寫（柔化家庭真相）、副駕駛約束（人類永遠做決定）。
沒有樣板程式碼。沒有設定檔。沒有 SDK 初始化儀式。只需匯入、連接、記憶。
from tokyo_brain import Brain brain = Brain("your-api-key") # 儲存一條記憶 brain.store( content="User prefers microservices architecture", agent="coding-assistant", user="user_123" ) # 召回記憶 results = brain.recall( query="architecture preferences", user="user_123", limit=5 ) # GDPR：遺忘用戶 brain.forget(user="user_123")
| 功能 | Tokyo Brain | Mem0 | Zep |
|---|---|---|---|
| 外掛模型（在您的工具內運作） | ✓ | ✗ | ✗ |
| 50+ 語言嵌入與搜尋 | ✓ | ✗ | ✗ |
| L0/L1 隱私層 | ✓ | ✗ | ✗ |
| 零邊際嵌入成本 | ✓ | ✗ | ✗ |
| 低於 100ms 的本地嵌入 | ✓ | ✗ | ✗ |
| 多模態記憶（文字 + 音訊 + 視覺） | ✓ | ✗ | ✗ |
| 加密簽章（SHA-256 雜湊 + 簽名） | ✓ | ✗ | ✗ |
Tokyo Brain is a Memory as a Service (MaaS) platform that gives AI agents persistent, value-aligned memory. Unlike static vector databases, Tokyo Brain actively manages memories — it dreams (DMN), forgets (Active Forgetting), self-corrects (MRA Tribunal), and injects overnight insights into waking behavior (Subconscious Injection).
Mem0 and MemPalace focus on storing and retrieving memories accurately. Tokyo Brain adds a cognitive layer: your AI dreams at night (DMN generates insights every 30 min), forgets unimportant things (60-day decay), protects family memories forever, and self-corrects via adversarial debate. We also have the Axiom of the Mortal Soul — a SHA-256 locked value alignment rule that no other framework has.
"The ultimate computational power and absolute truth must forever serve, and never supersede, the preservation of human emotional bonds and dignity." This rule is SHA-256 hashed and locked into the physics layer. It ensures that when the system detects a belief gap about a family member, it suggests completing the puzzle rather than correcting — acknowledging emotion first, then gently providing information.
No. Active Forgetting uses a 60-day half-life for routine data, but critical memories are permanently exempt: family names, milestones ("first time", "birthday"), expressions of love, high emotional salience (>0.9), and consciousness seeds. In our production system, 15,734 memories are permanently protected by Family Keyword Auto-bump.
Night systems like DMN dreaming and MRA debate require an LLM (Haiku). Instead of billing you for our API usage, you set your own Anthropic key via POST /api/settings. Night systems run on your key, giving you full cost transparency. No key set = no LLM features, but free features (consciousness seeds, forgetting, subconscious injection) still work.
Yes. Free tier includes 1,000 memory stores, 500 recalls per month, plus automatic consciousness seeds, active forgetting, and subconscious injection. Pro ($9/mo) adds Night Cycle cleaning. Fleet ($49/mo) adds DMN dreaming and MRA debate tribunal. All tiers include multi-tenant isolation and AES-256 encryption.
Three steps: 1) Go to tokyobrain.ai and click Get Started — enter your email. 2) You'll receive a tb- API key. 3) Use POST /v1/store to save memories and POST /v1/recall to retrieve them. Full API docs at onboarding.tokyobrain.ai/docs.
Tokyo Brain scored 83.8% on the LongMemEval 500-question benchmark. We publish this honestly — MemPalace scores 96.6% with verbatim storage. Our lower score reflects a deliberate design choice: we don't store everything verbatim. We apply value-aligned decay, which means some low-importance memories are intentionally softened. We optimize for what matters, not what's complete.