Uteke Cloud / docs

Uteke Cloud docs

Uteke Cloud is the managed version of Uteke — agent memory with hybrid recall. No server to run: point your agents at the API below and manage keys from the keys portal. Prefer to self-host? The open-source build runs the same API from a single Docker image.

Base URL & auth

Every REST route is available under /api/v2 (and mirrored at /api/v1 for compatibility). Authenticate with your API key as a Bearer token — generate keys at /portal/keys. Keys are shown once at creation; store them safely.

Core endpoints

MethodPathWhat it does / when to call it
POST/rememberStore a memory (content, tags, metadata, namespace, type, importance, pinned)
After each conversation turn or session ends — write what is worth remembering.
POST/recallHybrid recall — vector + full-text fused (RRF). Query-time embedding
When answers need meaning, not just keywords: paraphrases and related concepts both hit.
POST/searchKeyword search — no embedding, plain full-text + substring fallback
Exact names, error strings, technical terms. Cheaper and instant (no embedding).
GET/listList memories (limit 1–100, filter by tag / namespace)
Browsing or syncing state — walk the workspace with limit + offset.
GET/memory/{id}Fetch one memory by id
You already know the id (from a previous recall/list) and want the full record.
POST/forgetDelete a memory by id
Removing wrong or superseded content on request.
GET/tagsList tags in use
Building filters or a tag picker for your UI.
GET/usageToday’s usage + plan + quota snapshot
Before heavy operations, or to show users where their quota stands.
GET/exportExport the workspace as NDJSON (manifest on line 1)
Backups and migration — your data is never locked in.
POST/importImport NDJSON or a JSON array (dedup, id/created_at preserved)
Moving from self-hosted to cloud, or restoring an export. Re-running is safe (dedup).
POST/mcpRemote MCP endpoint — JSON-RPC 2.0 over HTTP (protocol 2025-06-18)
Connecting MCP clients (Claude Desktop, Cursor, …) instead of raw REST. See Connect.

Room and document endpoints (/room/*, /doc/*) follow the same auth pattern — see the open-source API reference for full request/response shapes, which the cloud mirrors.

Common pitfalls

ProblemFix
Recalling right after a write returns nothingEmbeddings are applied asynchronously after the write. Write at end-of-turn; recall from the next turn on. Keyword /search works immediately.
Filtering by metadataMetadata is stored but not filterable. Put anything you plan to filter on into tags (then /list?tag=…).
Asking /list for more than 100 itemsThe limit is clamped to 1–100. Page with offset instead of raising the limit.
Storing secrets in memoriesContent is stored as-is — never retain credentials, tokens, or keys. Scrub before writing.
Expecting /search to rank by meaningSearch is lexical (full-text, substring fallback). For semantic matches use /recall.

Where to go next

  • Connect — first curl calls and MCP client configuration.
  • Import / Export — migrate a self-hosted workspace to the cloud, or leave with your data anytime.

Errors

Errors return a JSON envelope: { "error": code, "message": "…" }. Quota breaches answer 403 with an upgrade_url hint; monthly quota (e.g. exports) exhaustion answers 429.

Base URL for every example: https://your-deployment/api/v2 · Get a key at /portal/keys