RedCrown.aiRedCrown.ai Docs Open the app

CLI reference

Every redcrown subcommand and flag.

Environment variables

Keys a local redcrown eval reads from your shell. They never leave your machine during a local eval.

VariableProvider
OPENAI_API_KEYOpenAI
ANTHROPIC_API_KEYAnthropic
OPENROUTER_API_KEYOpenRouter
GROQ_API_KEYGroq
HUGGINGFACE_API_KEYHugging Face
DEEPGRAM_API_KEYDeepgram
GEMINI_API_KEYGoogle AI Studio
NVIDIA_API_KEYNVIDIA NIM
MISTRAL_API_KEYMistral
COHERE_API_KEYCohere
REDCROWN_CUSTOM_HTTPA custom OpenAI-compatible endpoint, as JSON (base_url, auth_header_name, auth_value, body_style, model)

redcrown attest

Download a signed attestation for a completed run

FlagDescriptionDefault
run_id
--outoutput file (default <run_id>-attestation.json)
--api-urlhttps://api.redcrown.ai

redcrown build-dataset

Build an experiment JSON from a public corpus (primock57, mmlu-pro)

FlagDescriptionDefault
sourcepublic corpus source (omit when using --from-csv/--from-jsonl)
--outpath to write the experiment JSON
--limitcap the number of (audio, reference) items
--corpus-dirpath to an existing corpus checkout (skips cloning)
--quality-barquality bar a candidate must clear; default = the dataset's published bar (mmlu-pro 0.75), NOT 0.0
--monthly-minutesprojected monthly audio minutes for the $/mo column20280
--no-clonedo not clone; require --corpus-dir to point at a checkoutFalse
--ids-filepath to a newline-separated list of clip ids; builds exactly those items (the pinned benchmark subset). Applied after --limit, so do not combine them
--from-csvbuild from a CSV with input + reference columns (text tasks)
--from-jsonlbuild from a JSONL with input + reference fields (text tasks)
--tasktask kind for --from-csv/--from-jsonl
--input-colinput column/field name (default 'input')input
--reference-colreference column/field name (default 'reference')reference

redcrown eval

Run an experiment JSON locally and print the report

FlagDescriptionDefault
pathpath to an experiment JSON file
--samplerun a bundled offline sample with the demo provider (no keys)
--report-jsonalso write the full results (receipts included) as an upload-schema JSON for redcrown push
--audio-basebase URL for per-item audio (item_audio = base + id + .mp3)
--concurrencynumber of provider calls to run at once (default 1, sequential; raise it for many-candidate token benchmarks)1
--repeatrun each candidate N times and report a run-to-run quality stdev (default: the experiment's repeat_n, or 1). Note: this makes N times the API calls, so N times the eval spend. Tip: set params.seed on a candidate for a provider that supports seeded sampling.
--judgejudge panel member for quality_metric judge; repeat for a panel (e.g. --judge openrouter:openai/gpt-5.5)

redcrown import-results

Upload a locally-run eval's aggregated results JSON into RedCrown

FlagDescriptionDefault
pathpath to a results JSON file (the upload schema)
--api-urlRedCrown API base URLhttps://api.redcrown.ai
--tokenaccess token (or set REDCROWN_TOKEN); your RedCrown/Supabase bearer token

redcrown login

Log in to RedCrown (device flow; opens a code page)

FlagDescriptionDefault
--api-urlRedCrown API base URLhttps://api.redcrown.ai

redcrown logout

Delete the stored RedCrown credentials

redcrown push

Push a local eval's results JSON to RedCrown as a cloud run

FlagDescriptionDefault
pathresults JSON from `redcrown eval --report-json`
--api-urlhttps://api.redcrown.ai
--app-urlhttps://app.redcrown.ai
--orgworkspace (org) id; default personal org
--experimentappend the run to this standing experiment id
--no-receiptsstrip per-item receipts/references before upload (confidential outputs never leave this machine)False
--proof-linkmint and print a shareable proof link for the pushed runFalse

redcrown rejudge

Re-score an existing report-json's stored outputs with a new judge panel

FlagDescriptionDefault
pathresults JSON from `redcrown eval --report-json` (with receipts)
--judgepanel member; repeat for a panel
--keep-existingfold the original run's judge into the new panelFalse
--outpath to write the re-judged report JSON
--concurrency8

redcrown verify

Verify a RedCrown attestation file offline

FlagDescriptionDefault
path
--keya JWKS file to verify against (offline); default: fetch the file's key_url

Generated from source. Last verified .