---
source: src/main.rs
expression: root_help
---
Lossless storage and semantic search for sessions from any AI agent client
pond [VERSION]
Usage: pond [OPTIONS] <COMMAND>
Commands:
Setup
init Set up pond (idempotent: safe to re-run)
adapters Choose which adapters pond sync ingests
storage Probe and switch storage destinations
creds Manage URL-scoped credential sets
schedule Manage the automatic sync schedule
config Inspect configuration
Data flow
sync Make pond current: import, embed, index
optimize Embed the backlog, then fold the indexes
copy Copy data between stores, archives, JSONL
Query
search Search stored messages
get Fetch a session or message
sql Run one read-only SQL query
status Show pond health, data, and adapters
Serve
serve Run the HTTP API server
mcp Serve the MCP tools over stdio
Shell
completions Generate shell completions
skill Print the agent-onboarding SKILL.md
help Print this message or a subcommand's help
Options:
--storage-path <URL>
Storage destination: a local path or remote URL.
Accepts a bare path, `~/path`, `file://`, `s3://bucket/prefix`, `s3+https://host/bucket/prefix`, `gs://`, `az://`, or the keyword `local` (the platform default local data dir). Default: `[storage].path` from config, then the platform data dir (`~/.local/share/pond`).
[env: POND_STORAGE_PATH]
--config-file <PATH>
Config file to read (default: `~/.config/pond/config.toml`)
[env: POND_CONFIG_FILE]
-v, --verbose...
Increase logging verbosity
-q, --quiet...
Decrease logging verbosity
-h, --help
Print help (see a summary with '-h')
-V, --version
Print version
Getting started:
pond init set up storage, adapters, 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.