Structured AI decisions with probabilities for developers
A control room for Claude Code agents
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Paid
Open source
Pricing
Starter: $9.9 with 100,000 credits, no expiry; Pro: $99 with 1,000,000 credits, no expiry; Enterprise: $999 with 11,000,000 credits. One-time plans do not auto-renew; credits remain available after purchase.
Free. The code is on GitHub under Apache 2.0. A future hosted team office feature will be paid.
Key features
Typed decision output with Choice, Score, and Noul question types
Probability and confidence results on every answer
Online playground for testing with unlimited runs
REST API and SDK integration
Multiple concurrent requests
Team workspaces and collaboration
Up to 8 typed questions per request
Fast decision latency around 120ms
Agent Skill for coding agents and LLM workflows
Support for English and Simplified Chinese
Multi-agent monitoring from a single screen
Real-time status visualization with color-coded states
Tool approval and command authorization
Team workflows with task handoffs
In-conversation steering without window switching
System notifications for approval requests
Local-only architecture with no data leaving machine
Auto-deny protection for undecided requests
Integration with existing Claude subscription
What makes it different
Structured output with defined answer space
Probability-backed decisions code can use directly
Multiple questions from one state in parallel
Developer control over business logic and actions
Designed to integrate into existing systems without replacement
Complete local-first privacy: code and transcripts never leave your machine
No configuration or learning curve: read a room and you can run it
Works with your existing Claude Code installation and subscription
Open source under Apache 2.0 with no account required