Remote storage

Sync lore to the hosted LoreKit MCP server so your memories are available on every machine, from every agent, without any extra setup on each device.

Tip:

You can use the hosted instance at lorekit.io or self-host your own. This tutorial uses the hosted instance. For self-hosting see the Installation Guide.

Generate an API token

Go to Settings → API keys and click Generate new token. Enter a name (e.g. claude-local, ci-prod) and choose a permission tier:

lk_rw_… — read + write (agents that learn)
lk_ro_… — read only (CI context injection)
lk_wo_… — write only (one-way memory feeders)

The token is shown once only — copy it before closing the modal.

Point your agent at the MCP server

The fastest path is npx @lorekit/cli install — it scaffolds the skills, wires the MCP server, and installs the lifecycle hooks in one command. Or add the endpoint manually to your agent's MCP config:

// .mcp.json (Claude Code / Cursor / opencode — project-local)
{
  "mcpServers": {
    "lorekit": {
      "command": "npx",
      "args": ["-y", "mcp-remote",
               "https://pqokxlhvnosogizsjztg.supabase.co/functions/v1/mcp",
               "--header", "Authorization:Bearer lk_rw_<your-token>"]
    }
  }
}

Tip:

Keep .mcp.json out of version control — it contains your token. Commit a .lorekit.json instead to set the team default mode (e.g. { "mode": "remote" }).

Verify the connection

npx @lorekit/cli doctor

The doctor command checks connectivity, token permissions, and scope health. Look for the Remote section in the output — it should show a green ok status.

Two of those checks answer different questions, and both must be green:

connectivity probes the public /health function. It proves the network path only — it stays green for a token that no longer works.
authentication makes one authenticated request and reports what the server said about the token. A revoked or deleted token fails here with HTTP 401, and doctor exits non-zero. A write-only lk_wo_* token passes with a note that it has no read permission.

Tip:

Seeing authentication — token REJECTED? The token was revoked or deleted. Generate a new one at lorekit.io, then run npx @lorekit/cli install --force — it asks whether to keep, replace, or remove the token already in your config.

Write and read a memory

Write a test memory via the MCP endpoint:

memory.write {
  scope: "global",
  key:   "hello-remote",
  value: "Remote lore is working."
}

Read it back from any machine:

memory.read {
  scope: "global",
  key:   "hello-remote"
}
// → { "value": "Remote lore is working.", "updated_at": "…" }

Use in CI / GitHub Actions

Store a read-only token as LOREKIT_TOKEN in your repo secrets, then inject global memories before any AI step:

- name: Inject LoreKit context
  run: |
    curl -s -X POST "$LOREKIT_MCP_URL" \
      -H "Authorization: Bearer $LOREKIT_TOKEN" \
      -H "Content-Type: application/json" \
      -d '{
        "jsonrpc": "2.0",
        "id": 1,
        "method": "tools/call",
        "params": {
          "name": "memory.list",
          "arguments": { "scope": "global", "limit": 20 }
        }
      }'
  env:
    LOREKIT_MCP_URL: https://pqokxlhvnosogizsjztg.supabase.co/functions/v1/mcp
    LOREKIT_TOKEN: ${{ secrets.LOREKIT_TOKEN }}

(Optional) Install the GitHub App

To have LoreKit automatically learn from PR review comments, go to Settings → Integrations and install the LoreKit GitHub App. Every repository you grant it is covered instantly — there is no per-repo secret to copy and no webhook to configure on GitHub:

Covers: every repo you grant the App, as you add or remove them on GitHub
Learns from: resolved pull request review comments and reviews
Tags each memory: source::pr-webhook

Note:

Next steps: share memories with your whole team by setting up an organization. See the Team sharing tutorial.