Free: 200 daily credits every day. Credits refresh at midnight in account's time zone and do not roll over. A typical task uses about 15 credits, covering about 13 typical tasks per day.
Community: Free (open artifacts, self-serve). Team: $2,500 per month (launch pricing). Governed Evidence Pilot: $15,000 flat for 30 days (launch pricing). Enterprise: Custom annual contract with own hardware. Per-call API: $0.02 USDC for OpenAI-compatible chat and completions, $0.05 USDC for mesh an
Key features
Natural language task description
Background task execution for hours or up to 14 days
Personal Muze.bot email address
Email approval workflow
File handling and management
Web research and browsing
Task progress visibility
Source tracking and transparency
Daily credit system
Task continuation after email replies
Policy gates before AI agent actions
Signed hash-chained receipt ledger
Offline verification capability
Evidence synthesis through Second Brain
Mapped controls for ISO/IEC 42001, EU AI Act and NIST AI RMF
Air-gap deployment on own hardware
Hardware-key signing with user's own keys
Evidence-plane sidecar for agent stacks
Auditor export bundle
Open receipt specification and format
What makes it different
Operates in the background autonomously while you step away
Conversational interface without forms or strict prompts
Personal email address that keeps your inbox separate
User approval required for external emails
Every decision sealed into verifiable offline receipts
Eight core formulas proven in Lean 4
Explicit labeling of claims as declared, simulated or roadmap
No hidden paywall metrics—usage counted in signed receipts you verify