Skip to main content
Last updated on
Tags:
Options
Open in ChatGPTAsk ChatGPT about this pageOpen in ClaudeAsk Claude about this page

Getting Started

OpenBox adds governance, compliance, and audit-grade evidence to your AI agents. Choose your integration below to get started.

Choose Your Integration​

Claude Code
Governance for the coding agent itself, via Claude Code's hooks system. Every prompt, file edit, and shell command is governed.
HooksDev sessions
CrewAI
Governance for multi-agent crews and collaborative workflows. Every agent action is tracked automatically.
PythonMulti-agent
CopilotKit
Put OpenBox on top of CopilotKit. These docs use LangGraph as the current backend example.
TypeScriptLangGraph
Cursor coming soon
Governance for Cursor IDE agents via hooks. Every prompt, shell command, MCP call, and file read is governed.
TypeScriptIDE Hooks
Deep Agents
Per-subagent governance for DeepAgents workflows. Every nested call is captured automatically.
PythonSub-agents
LangChain
Python middleware governance for LangChain agents, model calls, tools, and hook-level telemetry.
PythonMiddleware
LangGraph
Governance for graph-based, stateful agent workflows. Every node and state transition is recorded.
PythonGraph workflows
Mastra
Governance for TypeScript AI agents and tool calls. Your existing Mastra code stays unchanged.
TypeScriptAgents
n8n
Govern your AI Agent node with one node swap. Your Chat Model, Memory, and Tool connections stay unchanged.
JavaScriptTypeScriptWorkflows
OpenRouter
Governance for OpenRouter agents, plus proof of which upstream provider actually served each prompt.
TypeScriptProvenance
OpenClaw coming soon
Tool governance and LLM guardrails for OpenClaw agents. Every tool call is evaluated against your policies.
TypeScriptTool governance
Temporal
Add the OpenBox plugin to your Temporal worker. Your existing workflows and activities stay unchanged.
PythonOrchestration

What OpenBox Captures​

From a single integration point, every execution is automatically governed:

  • Event timeline: workflow starts, completions, failures, and signals captured in sequence
  • Activity tracking: every activity execution with full inputs and outputs
  • HTTP call recording: all outbound requests (LLM calls, external APIs) with request and response bodies
  • Governance decisions: each event evaluated against your policies in real-time: allowed, constrained, approved, blocked, or halted
  • Session replay: step-by-step playback of the entire agent session for debugging and audit