An AI panel debates your goal; a referee rules on re-checkable evidence
The open-source AI agent for company-wide work
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
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.
Community (free): open-source self-hosted version with core agents, search, integrations, and community support. Business: $10/user/month billed annually, includes all core AI agent features, all integrations, SAML/OIDC single sign-on, priority email support, guided onboarding. Enterprise: custom pr
Key features
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
Task execution across multiple tools
Permission-aware context retrieval
Support for commercial and self-hosted models
Hybrid search with BM25 and semantic search
Source citations for answers
Cost and token visibility by team and model
Code execution in sandboxed environments
25+ workplace connectors
Audit logs and compliance controls
What makes it different
Referee decides on evidence, not argument quality
Panel from different vendors fails in different directions
Stuck is a targeted question, not model thrashing
Cost grows with ledger, not round count
Published matches become research record
Open source with Apache 2.0 license allowing inspection and self-hosting
Single unified system replacing multiple specialized tools
Model-independent context layer avoiding re-ingestion when switching providers
Full cost transparency and token tracking across all models
Flexible deployment with managed or self-hosted options
Referee.chat
Omni