Get Started

Platform Overview

The managed memory layer for AI agents — production-ready, EU-hosted.

Korely Agents turns scattered agent conversations into typed, bi-temporal facts your agents can recall across sessions. We run the store, the embeddings, the entity graph, and the contradiction checks; you call add() and get_context(). One key authenticates three surfaces — the SDK, the CLI, and the REST API.

flowchart LR
  A([Your agent]) -->|add| K[Korely]
  K --> E[Embed memory]
  K --> G[Entity graph]
  K --> F[Typed facts<br/>valid_from / invalid_at]
  G -.->|anchors| F
  A -->|get_context| R[Assemble active facts<br/>+ relevant memories]
  F -.-> R
  E -.-> R
  R --> P([Prompt-ready block])

Why it matters

• Continuity across sessions. Memories and facts persist per end user and per agent, so your agent stops asking the same question twice.
• Managed, nothing to host. Postgres + pgvector, the entity extraction, and the bi-temporal fact pipeline run on our infrastructure. No provisioning, no tuning.
• Current truth, not just nearest neighbours. Every memory is mined into (subject, predicate, object) facts with valid_from / invalid_at. When something changes the old value is invalidated, not deleted — and you can time-travel with as_of.
• EU sovereignty. Stored and processed in the EU (Helsinki), on our own infrastructure, on every tier.

What you get

• Three surfaces, one key. The Python and Node SDK, the CLI, and the REST API — all authenticated by one kor_live_ key.
• Fact-assembled recall. get_context() assembles your end user’s currently-valid typed facts into a prompt-ready block — this is the primary recall path, not nearest-neighbour guesswork. Semantic vector search() is there when you want raw memories. See Get context.
• A real graph. Entities link memories across your store and drive the typed facts that get_context() assembles. See The graph.
• Retrieval, not generation. No LLM runs on the read path. Fact and graph reads are pure SQL; semantic search and get_context add only a fast query embedding. Nothing generates the answer, so reads stay fast and cheap. See Architecture.
• Human in the loop. The same memory is inspectable and editable by a person in the Korely app — correct a fact, or erase everything about a user with one call. See Human in the loop.

Choose your path