Remember everything

Remember
everything.

Where ChatGPT keeps free-form notes, lynox builds a persistent Knowledge Graph that compounds. As you work, it captures the entities that matter and the relationships between them, and surfaces them in your next conversation — across threads, not just the one you're in.

Entity-aware memory

People, organizations, projects, products, locations, concepts — lynox recognizes entities and connects them automatically. "Sarah from Acme" becomes a node, linked to her company, her deals, and every conversation you've had.

Contradiction detection

"Last month you said Acme's budget is 50K. Their latest email says 80K." lynox flags conflicts instead of silently overwriting. You decide what's current.

Relationship mapping

Entities don't exist in isolation. lynox maps how they connect — who works at which company, which project belongs to which client, what a decision was based on.

Semantic search

ONNX embeddings power search across your entire knowledge base. Ask "what did we discuss about pricing" and get results from any thread, any entity, any date.

It knows who you mean.

Draft a note to Sarah at Acme about the pilot.

Recognized: Sarah Chen — CTO at Acme

Linked: the Acme project and your pilot notes

Composing with that context

Draft ready — it pulls in the pilot scope and Sarah's role. Sends when you confirm.

No re-explaining who Sarah is. lynox recognized the entity and pulled what it already tracks.

Most AI tools search text —
lynox builds a graph.

Retrieval-Augmented Generation searches documents. A Knowledge Graph understands structure. It knows that Sarah is the CTO of Acme, that Acme's deal is in negotiation, and that Sarah prefers calls over emails — without you asking. And because every part of lynox reads the same graph, the workflow that runs tonight knows what you learned in chat this morning.

Day 1

10 entities. Your first contacts and projects.

Month 1

200+ entities. The graph gets denser, and the next answer starts with your business already in context.

Month 6

1,000+ entities. Your business graph. Searchable, connected, yours.

Everything it tracks.

entity · Acme AG
node Acme AG — organization
people Sarah Chen (CTO) · Tom Ray
projects Q3 pilot
tracks role · topics · preferences
recall ONNX embeddings + graph
store SQLite · on your server

Every node, link, and embedding lives in a local SQLite file. Copy it anywhere — it's yours.

Built for permanence.

Storage SQLite — no external database, runs on your server
Search ONNX embeddings — fast semantic search, runs locally
Resolution Entity deduplication — "Sarah Chen" and "S. Chen" resolve to one node
Traversal Recursive CTE queries — multi-hop relationship navigation
Languages Multi-lingual — entities in any language, cross-language search
Export Your data, your files — copy the SQLite database anytime