OreCloud docs
Context storage for AI agents. Store user context and recall it as a prompt-ready block.
OreCloud is a managed memory store for agentic apps. Each end user of your app gets their own store, created automatically on its first write. A store is their own instance of LodeDB, the open-source embedded vector database. Embedding runs server-side, so there is no vector infrastructure to run.
from lodedb.cloud import Client
client = Client()
memory = client.store("user-42")
memory.add("likes hiking near Seattle")
context = memory.context_block("plan my weekend")Quickstart
Store and recall your first memory in under two minutes.
Working with memory
add, recall, context_block, TTLs, provenance, and forgetting.
Hosted MCP
Every store is an MCP server. Connect an agent with one command.
Keys & environments
Environment-bound keys, scopes, and double-gated text access.
Portability
Pull a store to disk and open it locally, no lock-in.
SDK & CLI reference
The Python client surface and the lodedb cloud command tree.
Limits & errors
Plan limits, request caps, and every typed refusal.
For LLMs
These docs are also served in machine-friendly renderings: /llms.txt
(index), /llms-full.txt (everything as one markdown
document), and any page as raw markdown by appending .md to its URL.