Skip to main content
The mirrors CLI is a terminal client of the hosted backend with full parity with the web app: anything you can do in the UI you can do from the CLI — log in, ingest and build a twin, explore it, run it, add business context, apply agent-suggested fixes, and author + run evals. It talks only HTTP to the backend; it has no engine or build logic of its own.

​
Install

It ships in the Python mirrorkit package behind the cli extra: 
pip install "mirrorkit[cli]"   # adds the `mirrors` command

​
Log in

Authenticate with a workspace API key (mk_live_…, minted in the web app under Settings → API keys): 
mirrors login    # paste the key (or --api-key / --dev)
Credentials live in ~/.mirrors/config.json. For CI, set MIRRORS_BASE_URL / MIRRORS_API_KEY instead.

​
Commands

mirrors env ls                                 # list environments
mirrors build traces.jsonl --name airline      # ingest + build a twin (streams the log)
mirrors build --project airline --name airline # build from a collector stream

mirrors env assets <env>                       # explore the twin…
mirrors env schema <env>
mirrors env fidelity <env>
mirrors env drift <env>
mirrors env traces <env>

mirrors query <env> "cancel my flight"         # run the twin (one-shot) + see the trace
mirrors chat <env>                             # multi-turn conversation with the twin
mirrors container status|start|stop <env>      # its hosted HTTP endpoint

mirrors context add <env> --text "…"           # business context that lifts fidelity
mirrors proposal new <env>                     # agent-suggested changes…
mirrors proposal accept <env> <id>             # …accept -> rebuild

mirrors eval generate <env> --save-as smoke    # auto-author eval cases
mirrors eval create <env> --name smoke --from cases.json
mirrors eval run <eval-set-id>                 # run evals
mirrors run show <run-id>                      # inspect a run

mirrors usage                                  # task-minutes vs. plan allowance
Add --json to any command for machine-readable output — handy in scripts and CI.

​
Typical flow

1

Build

mirrors build --project my-agent --name my-agent turns collected traces into a runnable twin, streaming the build log.
2

Explore and query

mirrors env fidelity my-agent shows per-tool scores; mirrors query my-agent "…" runs a session and prints the trace.
3

Eval

mirrors eval generate my-agent --save-as smoke auto-authors cases from your traces, then mirrors eval run <id> scores the agent against them.