1 · AI Chatbot
Ask your own knowledge anything
Upload documents and spreadsheets and ask in plain language. Use Dorothy, Claude or ChatGPT through MCP, or your own chat app.
From: the Free plan.
Learn more →Panaxon AI · M.N.E.M.O.
One memory for your AI. Chat with it, share it, build on it.
M.N.E.M.O. is a memory platform that stores what you know and gives back the exact fact you stored, not the closest match by similarity. Chat, sharing and your own pipelines all use the same memory, so you start with what you need and use more of the platform as your plan grows.
One platform, three products
Three ways to use one memory.
These are not three separate products to buy. They are three parts of one platform, built on the same memory, and your plan decides which features you can use. Whatever one can see, the others can see, so you can add them later without moving any data.
2 · Knowledge Sharing Network
Share knowledge, not documents
Publish a subject privately or publicly. Others subscribe and ask questions of it, and you stay the owner.
From: Free to subscribe, Standard to publish and share.
Learn more →3 · MnemoRAG
One call from your own pipeline
Skip building a RAG pipeline. Define an endpoint over your subjects and call it from your app, bot or workflow.
From: the Pro plan.
Learn more →The memory underneath
All three run on the same memory: exact recall, not approximate similarity.
Retrieval-augmented generation just means retrieving context before generating an answer. Vector search — approximate nearest-neighbor lookup over dense embeddings — is the common way to do that retrieval, not a requirement of it. M.N.E.M.O. does RAG through OAT, a patent-pending deterministic index: a query resolves to the exact stored fact, not the closest match by distance. That doesn't eliminate every source of error an LLM can introduce, but it removes the biggest one — being handed the wrong context in the first place, and not knowing it.
Predictable latency
Indexed retrieval is designed to fetch data directly, avoiding the variable cost of scanning approximate matches.
Scale without drift
Structured, hierarchical indexing is built to hold up as memory volume grows, not just at small scale.
Exact recall
Deterministic lookups are intended to reduce the drift that comes from approximate similarity matching.
Start anywhere
One account. Your plan decides how much of the platform you use.
Every plan runs on the same memory. Moving up a plan switches on more of the platform, with nothing to migrate.
| Plan | What you can use |
|---|---|
| Free | The AI chatbot with a limited monthly allowance, and subscribing to knowledge shared with you |
| Standard | Everything in Free, plus publishing and private sharing, API access, and the MCP connector and Claude Code Skill |
| Pro | Everything in Standard, plus MnemoRAG, multiple users and role-based access rules |
| Enterprise | Everything in Pro, with negotiated usage, more model choice and dedicated support |
See it live
Dorothy: a reference app built entirely on M.N.E.M.O.
Dorothy is Panaxon AI's own conversational interface, showing what persistent, structured memory feels like day to day. It's one example of what the API can power, not a limit on what you can build with it.
Next step
Start with what you need
Try Dorothy to chat with your own knowledge, or talk with Panaxon AI if you are building agents, copilots or memory-heavy pipelines on M.N.E.M.O.