---
source: src/main.rs
expression: root.render_long_help().to_string()
---
Lossless storage and hybrid search for sessions from any AI agent client
Usage: pond [OPTIONS] <COMMAND>
Commands:
init Set up pond (idempotent: safe to re-run)
sync Make pond current: import, embed, update indexes
status Show pond health, data, and source status
search Search stored messages
get Fetch a session or message
sql Run one read-only SQL query over the corpus
serve Run the HTTP API server (or MCP over stdio with --transport stdio)
mcp Serve the MCP tools over stdio (for agent clients)
schedule Manage the automatic sync schedule
storage Inspect, probe, and switch storage destinations
export Export a compact restorable .pond archive
import Restore a .pond archive
config Inspect configuration
completions Generate shell completions
help Print this message or the help of the given subcommand(s)
Options:
-h, --help
Print help (see a summary with '-h')
-V, --version
Print version
Global options:
-v, --verbose...
Increase logging verbosity
-q, --quiet...
Decrease logging verbosity
Getting started:
pond init set up storage, sources, MCP, and scheduling
pond sync import new sessions, embed, update indexes
pond search "that auth refactor" find past work
claude mcp add -s user pond -- pond mcp register pond as an MCP server in Claude Code
Every command documents itself: `pond <command> --help` carries examples.