Monitor quotas, tokens and coding agent sessions from your screen edge on Mac, iPhone and Apple Watch
Trust layer for AI agents with deterministic gating, isolated execution, and proof for every action
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Not given
Pricing
Agent HUD (Mac app): Free. Agent HUD Remote: From $2.99 a month (1 Mac early-bird price), $4.99 regular; yearly plans from $29.99 early-bird to $49.99 regular. 2 Mac plans: $4.99/$7.99 monthly, $49.99/$79.99 yearly. 3 Mac plans: $5.99/$9.99 monthly, $59.99/$99.99 yearly. First week free on all plans
Not given
Key features
Quotas, balances and reset times displayed at screen edge with color-coded status indicators
Approve or deny tool calls and answer agent questions directly from the HUD
One-click navigation back to any session's thread, tab or terminal pane
Three display modes: Notch, Simple and Dynamic for different screen layouts
Detailed token usage analysis by time, agent, model, session, turn and call
Built-in MCP server for agent-to-agent communication
iPhone and Apple Watch apps with iCloud sync for remote access
Voice input on Apple Watch to create new sessions
Deterministic gate that decides before running language models
Isolated code execution with sandboxing and micro-VMs
Append-only audit logs with SHA-256 manifests and hash-chained verification
Honesty measurement under load across multiple nodes
Fleet management with trust plane for machines
OpenAI-compatible endpoints and MCP support
49% UI grounding capability on 600 tasks
95.2% tool calling accuracy
31.6 milliseconds p50 task latency
0.43% false claim rate on 12,344 recorded actions
What makes it different
Unified view of quotas and sessions for 18 agents on one screen edge
Built-in MCP server allows agents to communicate with each other and customize the UI
Works offline on iPhone with cached data and requires no separate account
End-to-end encrypted iCloud sync for Agent HUD Remote with no server access to data
Complete auditability with cryptographic proof for every action
No vendor lock-in with open standards and open source
Measured honesty benchmarks with 0.43% false claim rate
Production-ready with verified open source repositories and green CI
Agent HUD
gamAI