Live demo

One agent identity. Four agents running.

Claude Code internally spawns multiple sub-agents: planner, file ops, executor, validator. Every tool call arrives at the MCP proxy wearing the same badge: claude-code. Behavry records which of them actually acted.

/001 · THE DEMOBEHAVRY · RECORD

Run the agents. Watch the record form.

Pick a task, run it, and watch every tool call get intercepted, scored, and hash-chained into a Decision Trace before it fires. This simulation requires JavaScript; the rest of the page does not.

0 intercepted 0 blocked 0 escalated
Claude Code internal
Claude Code spawns sub-agents
internally · each with its own
identity and intent
Behavry proxy · inline execution path
Proxy active · all MCP traffic intercepted before execution
Every tool call passes through
before it fires
Decision Trace
Causal chain-of-custody
artifact · not a log
/ONWARDBEHAVRY · RECORD
  • THE DECISION TRACE

    What the agent did, why it was allowed, and a record anyone can verify without us.

  • ARCHITECTURE

    One vantage point in the path of the action, across supported agent surfaces.

  • COVERAGE

    Eight ways an agent gets in, and where each one is intercepted.

Every tool call intercepted. Every decision traced.

BOOK A DEMO →MSP or MSSP? Discuss a pilot →