2.5 KiB
| title | description |
|---|---|
| CLI Reference | ReMe command syntax, service invocation, configuration overrides, and plugin commands. |
CLI Reference
The basic syntax is:
reme ACTION key=value ...
Start an Application
Use two stages: start a service in one terminal, then call Jobs from another. Choose one startup command and leave it running:
reme start
reme start config=demo
reme start workspace_dir=/data/reme service.port=8181
Plain start runs the configured Service. Omit config to use default; select another configuration when needed.
Call Jobs
In another terminal, each action name is a Job name. The CLI discovers the running service configuration:
reme help
reme health_check
reme search query="project decision" limit=10
reme read path=digest/wiki/project.md start_line=1 end_line=80
Use JSON for structured values:
reme auto_memory \
session_id=example \
messages='[{"role":"user","content":"Remember this preference"}]'
Client-selection arguments—backend, transport, host, port, timeout, command, args, and show_metadata—configure the client and never leak into the Job payload.
Configuration overrides
reme start \
config=/path/to/custom.yaml \
service.port=8181 \
service.web_enabled=false \
plugins='["auto-fin"]'
Leading - or -- is optional. Use dots for nested keys and JSON for arrays and objects.
Service discovery
reme find_reme
This reports a discovered service but never starts or replaces a process.
Plugin commands
Package management runs locally rather than through HTTP or MCP:
reme plugins list
reme plugins show auto-fin
reme plugins validate auto-fin
reme plugins install plugins/auto-fin
reme plugins uninstall auto-fin
See Plugin Management for the complete workflow.
Discover active capabilities
The Job API Reference describes the default configuration. Plugins and custom YAML may change the running service, so automation should prefer:
reme help
reme app_config
Run Once Without a Persistent Service
For a script that needs to execute one Job and exit, use the one-shot CLI Service:
reme start config=default job=search query="keywords" limit=5
start job=<name> runs the Job locally through the normal application lifecycle and then exits. It does not call an
already running service. Normal interactive examples use the two-stage workflow above.