MenteDB | The Mind Database for AI Agents

Open source, Apache 2.0Beta

Your AI's memory,<br>engineered from scratch<br>A Rust database that pre digests knowledge for single pass transformer consumption. Not a wrapper. A ground up storage engine that thinks.<br>View on GitHubTry the DemoGet Started

The Problem<br>AI has a memory problem<br>Current AI systems consume context in a single pass with no ability to revisit, reflect, or recognize what they are missing.

One Shot Consumption<br>AI gets a single context window. No re-reading, no follow ups. Every token must count.

Zero Self Awareness<br>AI can't sense what it doesn't know. It can't feel uncertainty or detect its own knowledge gaps.

Flat Context, Associative Thinking<br>AI reads linearly but attends associatively. Raw text dumps waste compute on noise.

Why MenteDB<br>Your agent.md has limits<br>Static instruction files work for small projects. But as context grows, decisions accumulate, and you work across devices, you need something that actively manages knowledge for you.

Without MenteDB

You manually update agent.md every time something changes

Finding past decisions means grep-ing through a flat file

Contradictions go unnoticed until something breaks

Past mistakes are forgotten and repeated

Context lives on one machine only

File grows until it blows the context window

With MenteDB

AI extracts facts, preferences, and decisions automatically

Semantic search finds relevant memories across sessions

Contradictions are flagged the moment they appear

Pain warnings surface before you repeat a mistake

Cloud sync keeps every device on the same page

Thousands of memories, only the relevant ones retrieved

Automatic extraction<br>Your AI reads every conversation and decides what is worth remembering. Facts, preferences, decisions, and corrections are stored without you lifting a finger.

Semantic search across sessions<br>"What did we decide about auth?" works via embeddings, not string matching. MenteDB finds relevant memories even when you use different words.

Contradiction detection<br>If you said Postgres last month and MySQL this month, MenteDB flags the inconsistency. A static file cannot detect when your decisions change.

Pain warnings<br>Past mistakes surface automatically when you are about to repeat them. Anti-patterns you recorded are matched against your current context.

Cross-device sync<br>Your laptop and desktop share the same brain. Cloud mode means every device sees every memory instantly.

Scales beyond context windows<br>An agent.md works until it is too big for the context window. MenteDB stores thousands of memories and retrieves only the relevant ones via vector search.

Features<br>A cognitive engine, not just storage<br>Fifteen core systems that transform MenteDB from a database into an active participant in your AI's reasoning.

Sleeptime Enrichment<br>Background pipeline extracts semantic facts, links entities, detects communities, and builds user profiles from raw conversations. Like the brain consolidating memories during sleep.

Stream Processing<br>Continuous memory ingestion with real time belief updates as conversations unfold.

Write Inference<br>Automatically derives new knowledge from stored memories at write time, not query time.

Trajectory Tracking<br>Maps conversation paths through topic space to predict where dialogue is heading.

Phantom Memories<br>Detects knowledge gaps and creates placeholder memories so the AI knows what it does not know.

Interference Shielding<br>Prevents contradictory memories from polluting context by isolating conflicting beliefs.

Pain Signals<br>Records negative feedback and emotional triggers to prevent the AI from repeating mistakes.

Speculative Pre Assembly<br>Predicts upcoming queries and pre builds context windows, like branch prediction for knowledge.

Bi-Temporal Validity<br>Memories carry valid_from/valid_until timestamps. Temporal invalidation instead of deletion, with point-in-time queries.

LLM Cognitive Inference<br>LLM judges whether new memories invalidate, update, or are compatible with existing ones. 100% accuracy on 62 test cases.

Hybrid Search<br>BM25 + HNSW vector + RRF fusion for best-of-both-worlds retrieval. Keyword precision meets semantic understanding.

ChatGPT & Cursor Ready<br>Claude Code hooks make memory automatic on every turn. The claude.ai connector, ChatGPT, Cursor, and Copilot connect with one URL.

Native SDKs<br>Rust, Python, and TypeScript bindings with native performance. pip install, npm install, or cargo add and start building.

API Key Management<br>Create, revoke, and monitor API keys from the dashboard. Scoped access control for teams and production deployments.

Webhooks & Delivery Logs<br>Get real-time notifications when memories change. HMAC-signed payloads with delivery logs, status tracking, and automatic retries.

Before & After<br>The difference memory makes<br>Same user. Same question. Completely different experience.

The Repeated MistakeThe Lost ContextThe Preference Drift<br>Without Memory

Deploy to production

Running...