Korely
Your Dashboard

Coding agents

Claude Code

Give Claude Code a hosted memory it reaches from every machine. One command connects the Korely MCP server, no OAuth dance, no package to install, just your API key.

Claude Code already carries knowledge across sessions with CLAUDE.md files and auto memory, notes it saves on your machine. Auto memory is machine-local: it stays on the computer where Claude Code wrote it. Korely adds a hosted memory that Claude Code reaches with the same key from every machine where you add the server. Before answering, Claude Code can pull the active typed facts and relevant memories it has stored, and write new ones as it learns. Facts are bi-temporal: when a model judge decides a new one replaces an earlier one, the old fact is closed with its end date, not overwritten, and as_of and known_as_of read what was true, or what the store knew, on any past date. The intelligence, entity and typed-fact extraction, contradiction resolution, bi-temporal validity, runs server-side. Claude Code just calls the tools.

Prerequisites

  • A Korely API key (kor_live_...). The hobby tier is free.
  • Claude Code installed (claude --version).

Add the Korely MCP server

Korely's agent memory is a remote MCP server at https://api.korely.ai/agent/mcp, authenticated with your key in a header, no browser login. Add it with one command:

Terminal window
claude mcp add --transport http korely https://api.korely.ai/agent/mcp \
  --header "Authorization: Bearer kor_live_..."

claude mcp add uses local scope by default: the server loads only in this project, on this machine. Add --scope user to make it available in all your projects on this machine. On another machine, run the same command with the same key and Claude Code reads the same memory.

Or add it to your project's .mcp.json directly:

{
  "mcpServers": {
    "korely": {
      "type": "http",
      "url": "https://api.korely.ai/agent/mcp",
      "headers": {
        "Authorization": "Bearer ${KORELY_API_KEY}"
      }
    }
  }
}

Export KORELY_API_KEY=kor_live_... in the shell that launches Claude Code, and approve the server when Claude Code asks about project-scoped servers.

Run /mcp inside Claude Code to confirm korely is connected.

Save every session without asking. In the repository, run korely init --tool claude-code (korely-memory 0.1.26 or later): hooks hand Claude Code the repository's memory when a session starts and save the session to it as a memory of kind session. It also replaces any MCP server named korely at local scope (user scope with --global), the one added above included, with a local server that runs on your machine; --no-mcp removes that entry and adds none. To keep the remote server, run korely init --tool claude-code --no-mcp first and add the server above afterwards. See Connect a coding assistant.

What Claude Code can do

Once connected, Claude Code has four memory tools:

ToolWhat it does
korely_get_contextThe recall path: assembles the active typed facts plus the most relevant memories into a prompt-ready block. Pure retrieval: the query is embedded once for the vector search, and no generative model runs on the read path.
korely_addStore a memory. Typed (subject, predicate, object) facts are extracted server-side, and a model judge closes the earlier fact, with its end date, when it decides a new one replaces it.
korely_searchSemantic search over stored memories, ranked.
korely_get_factsThe typed bi-temporal facts known about a user, with point-in-time queries: as_of (what was true then) and known_as_of (what the store knew then).

Use it

Now Claude Code reaches for memory on its own. Tell it something durable and it calls korely_add; ask it something personal and it calls korely_get_context first: 

You › Remember that this repo deploys to Hetzner, not Render.
      → korely_add("This repo deploys to Hetzner, not Render")


# next session, days later
You › How do we deploy this?
      → korely_get_context("deploy") → "This repo deploys to Hetzner..."
Claude › This repo deploys to Hetzner (you told me earlier), not Render. ...

Scoping

Every tool accepts an optional user_id so one key can serve many end users: a read that names "user-b" never returns a memory written for "user-a". Omit it on a write and the memory belongs to no end user (a key confined to one end user writes to that one). Omit it on a read and the read covers every end user the key can see.

Why this is more than a notepad. Korely keeps each memory's text as written and also extracts typed facts with bi-temporal validity from it. When something changes ("this repo now deploys to Hetzner, not Render"), the judge closes the old fact with its end date instead of overwriting it, so korely_get_context returns what's true now, and as_of can still replay what was true before. EU-hosted.

Related