For AI agents: a documentation index is available at https://www.mongodb.com/docs/llms.txt — markdown versions of all pages are available by appending .md to any URL path.
Docs Menu

agentengine memory configure

Upload project-level memory server configuration.

Upload the ‘memory:’ section of a project-config.yaml to the project’s stored memory config.

With no [path], the file is resolved the way ‘agentengine dev up’ resolves it: the nearest stack marker (an agent.yaml or a memory-only project marker) is found first, then the nearest project-config.yaml at or above that stack root, stopping at the repository root (a directory containing a .git directory). Only when no stack is found does it fall back to project-config.yaml in the current directory. A stack that resolves with no project-config.yaml is an error.

Only the memory sub-document is stored. The config is delivered to the memory server by a background worker and before the next ‘agentengine deploy’, but the memory server reads its config only at startup: run ‘agentengine memory apply’ to make it take effect.

Memory is project-scoped. The target project comes from --context, this directory’s pin, or explicit target flags. No initialized agent directory is required.

Examples:

agentengine memory configure
agentengine memory configure --context production
agentengine memory configure [path] [flags]
--base-url string Platform base URL
--context string Named context to target (see 'agentengine context list')
-h, --help help for configure
--org-id string Organization ID
--project-id string Project ID
-y, --yes Skip confirmation prompt
--log-file string override log file path
--log-level string file log verbosity (error|warn|info|debug) (default "info")
--no-log disable file logging
-q, --quiet silence stderr below error
-v, --verbose count raise stderr verbosity (-v info, -vv debug)
Rate this page