meridian-governance-cli

Scriptable command-line client for Meridian Governance Router, over meridian-client. Installs as the meridian command.

Not to be confused with the unrelated meridian-cli package also on PyPI.

Not a chat REPL and not mta-cli with the serial numbers filed off — Meridian doesn't have anything to chat with or a persona to pick. This is closer in spirit to the aws or stripe CLIs: subcommands over an API, scriptable, no interactive loop required.

Install

pip install meridian-governance-cli

Get credentials

meridian signup          # new org — prompts for org name, email, password
# or
meridian login           # existing account — authenticates, mints a new key
meridian whoami           # confirm what's saved

Credentials live in ~/.meridian/config.json (mode 600 — api_key is in there in plaintext, same tradeoff mta-cli makes for its own token). Override the location with MERIDIAN_CLI_HOME if you want more than one profile.

Commands

meridian resolve my_agent [--project-id ID] [--json]
meridian explain ROUTING_LOG_ID
meridian audit ROUTING_LOG_ID --input-tokens N --output-tokens N

meridian projects create --name NAME [--quality Q] [--cost C] [--risk R]
meridian projects list

meridian agents create PROJECT_ID AGENT_NAME [--pinned-model M] [--quality-override Q] [--allowed-hubs h1,h2]
meridian agents list PROJECT_ID

meridian keys list [--json]
meridian keys create [--name NAME]
meridian keys revoke KEY_ID

meridian catalog
meridian logout

Every data-returning command without a dedicated human-readable format (explain, audit, catalog, projects list, agents list) prints raw JSON — pipe into jq.

What this deliberately doesn't do

• No chat, no persona selection, no device integrations — those are mta-cli concerns (consumer AI Companion), not Meridian's. Meridian answers "which model should this agent use"; it has nothing to converse with.
• No hub/model/deployment registration commands — those routes aren't tenant-scoped today (console/house-key only), so a CLI command for them would just 403 for every real user. Added if/when that changes.
• No interactive REPL. If you want one, it'd be a thin layer calling the same functions cli.py already has — the commands are the primitive, not the shell.