Skip to main content

Behavry Integration — Open Interpreter

Open Interpreter connects to Behavry via stdio transport. It supports both local and remote LLMs. Because it has unrestricted shell access, Behavry classifies it at critical risk tier by default.

Prerequisites​

  • Behavry stack running (make dev or docker compose up)
  • Open Interpreter installed
  • Python 3.11+

Quick Setup​

make setup

Manual Configuration​

Add to ~/.openinterpreter/config.yaml:

mcp_servers:
  behavry:
    transport: stdio
    command: behavry-mcp-stdio
    args:
      - --server-url
      - http://localhost:8000
    env:
      BEHAVRY_CLIENT_ID: "<client_id>"
      BEHAVRY_CLIENT_SECRET: "<client_secret>"

Risk Tier: Critical​

Open Interpreter can execute arbitrary shell commands and write to any file. By default:

  • All shell commands are logged with full audit metadata
  • Destructive operations trigger HITL escalation
  • File writes to sensitive paths are blocked
  • DLP scanning runs on all output

Adjust the risk tier via the dashboard after enrollment if needed.

Local vs. Remote LLMs​

Behavry governs the tool execution layer regardless of the LLM backend. To also audit LLM API calls, configure the corresponding Behavry API proxy (OpenAI, Anthropic, Ollama, or Gemini) alongside this integration.

Verify​

  1. Start Open Interpreter: interpreter
  2. Ask it to perform an action
  3. Check http://localhost:5173 → Live Activity for the event