A personal assistant that coordinates your AI tools, agents and outside services
An AI panel debates your goal; a referee rules on re-checkable evidence
Stage
Startup
Not given
Founded
2025
Not given
Based in
Not given
Not given
Pricing model
Paid
Freemium
Pricing
Plans start at $20 USD per month with credit-based usage. New accounts receive 1,000 OC trial credits once per person with no card required. Additional credit packs available.
Free: $1.00 starting credit once. Credit plans from $10 top-up with no expiration. Your own key: 5% infrastructure fee after the first $5.00 of usage.
Key features
Hand work to coding agents like Claude Code and Codex
Interactive Canvas views for checklists, trackers and dashboards
Long-running tasks that continue across sessions
Visible memory graph you can browse and edit
Encrypted Secrets Vault for credentials and API keys
Choice of AI models from multiple providers
Panel of up to six AI models from different vendors
Referee rules on re-checkable evidence only
Searches academic databases: arXiv, OpenAlex, Crossref, Europe PMC
Executes Python code to verify claims
Customizable acceptance standards
Matches pause and resume without losing work
Shared ledger prevents re-derivation
Spending limit per match
What makes it different
Coordinates multiple AI tools and agents in one interface
Keeps credentials encrypted and away from language models
Tasks continue running across sessions without closing conversations
Transparent memory and audit logs for all actions
Works on Mac with direct access to files, apps and browser
Referee decides on evidence, not argument quality
Panel from different vendors fails in different directions
Referee.chat