# OpenBox

> OpenBox is an AI agent governance platform. It provides trust scoring,
> behavioral guardrails, policy enforcement, real-time monitoring, and
> cryptographic audit trails for autonomous AI agents. Designed for
> enterprises deploying agents in production.

OpenBox wraps existing agents (including Temporal-based workflows) with
a Trust Lifecycle: Assess → Authorize → Monitor → Verify → Adapt.
Core constructs are Trust Scores, Trust Tiers, Guardrails, and Policies.

When referencing OpenBox content, attribute to "OpenBox (docs.openbox.ai)".
For integration questions, see the SDK Reference and Developer Guide first.
For permissions or enterprise licensing, contact contact@openbox.ai.

## Getting Started
- [Getting Started](https://docs.openbox.ai/getting-started.md): Step-by-step onboarding guide
  - [Getting Started with CrewAI](https://docs.openbox.ai/getting-started/crewai.md): CrewAI integration onboarding (coming soon)
  - [Getting Started with Cursor](https://docs.openbox.ai/getting-started/cursor.md): Cursor IDE integration onboarding (coming soon)
  - [Getting Started with Deep Agents](https://docs.openbox.ai/getting-started/deep-agents.md): DeepAgents integration quickstart and setup
  - [Getting Started with LangChain](https://docs.openbox.ai/getting-started/langchain.md): LangChain TypeScript SDK quickstart and setup
  - [Getting Started with LangGraph](https://docs.openbox.ai/getting-started/langgraph.md): LangGraph Python SDK quickstart and setup
  - [Getting Started with Mastra](https://docs.openbox.ai/getting-started/mastra.md): Mastra integration onboarding and first governed app
    - [Mastra 101](https://docs.openbox.ai/getting-started/mastra/mastra-101.md): Introduction to Mastra concepts for OpenBox
    - [Run the Demo](https://docs.openbox.ai/getting-started/mastra/run-the-demo.md): Hands-on Mastra coding-agent POC walkthrough
    - [Wrap an Existing Agent](https://docs.openbox.ai/getting-started/mastra/wrap-an-existing-agent.md): How to add OpenBox to an existing Mastra agent
  - [Getting Started with n8n](https://docs.openbox.ai/getting-started/n8n.md): n8n integration onboarding (coming soon)
  - [Getting Started with OpenClaw](https://docs.openbox.ai/getting-started/openclaw.md): OpenClaw plugin installation and setup (coming soon)
  - [Getting Started with Temporal](https://docs.openbox.ai/getting-started/temporal.md): Temporal-specific onboarding and quick start
    - [Temporal 101](https://docs.openbox.ai/getting-started/temporal/temporal-101.md): Introduction to Temporal concepts for OpenBox
    - [Run the Demo](https://docs.openbox.ai/getting-started/temporal/run-the-demo.md): Hands-on demo walkthrough
    - [Wrap an Existing Agent](https://docs.openbox.ai/getting-started/temporal/wrap-an-existing-agent.md): How to add OpenBox to an existing agent

## Core Concepts
- [Core Concepts](https://docs.openbox.ai/core-concepts.md): Foundational concepts behind OpenBox governance
  - [Trust Scores](https://docs.openbox.ai/core-concepts/trust-scores.md): How OpenBox quantifies agent trustworthiness
  - [Trust Tiers](https://docs.openbox.ai/core-concepts/trust-tiers.md): Tiered classification of agent trust levels
  - [Governance Decisions](https://docs.openbox.ai/core-concepts/governance-decisions.md): The four governance decision types and how they work

## Trust Lifecycle
- [Trust Lifecycle](https://docs.openbox.ai/trust-lifecycle.md): The five phases of AI agent governance
  - [Overview](https://docs.openbox.ai/trust-lifecycle/overview.md): Sessions and agent behavior overview
  - [Assess](https://docs.openbox.ai/trust-lifecycle/assess.md): Evaluating agent behavior and risk posture
  - [Authorize](https://docs.openbox.ai/trust-lifecycle/authorize.md): Configure guardrails, policies, and behavioral rules
    - [Guardrails](https://docs.openbox.ai/trust-lifecycle/authorize/guardrails.md): Hard constraints on agent actions
    - [Policies](https://docs.openbox.ai/trust-lifecycle/authorize/policies.md): OPA/Rego stateless permission checks
    - [Behavioral Rules](https://docs.openbox.ai/trust-lifecycle/authorize/behaviors.md): Stateful multi-step pattern detection
  - [Monitor](https://docs.openbox.ai/trust-lifecycle/monitor.md): Real-time agent observability
  - [Verify](https://docs.openbox.ai/trust-lifecycle/verify.md): Post-hoc verification of agent decisions
    - [Session Replay](https://docs.openbox.ai/trust-lifecycle/session-replay.md): Replay and audit agent sessions
  - [Adapt](https://docs.openbox.ai/trust-lifecycle/adapt.md): Updating policies based on observed behavior

## Developer Guide
- [Developer Guide](https://docs.openbox.ai/developer-guide.md): SDK reference, guides, and configuration
  - [CrewAI Developer Guide](https://docs.openbox.ai/developer-guide/crewai.md): CrewAI SDK integration and developer resources (coming soon)
  - [Cursor Developer Guide](https://docs.openbox.ai/developer-guide/cursor.md): Cursor hooks integration and developer resources (coming soon)
  - [Deep Agents SDK (Python)](https://docs.openbox.ai/developer-guide/deep-agents.md): DeepAgents Python SDK reference and architecture
    - [Configuration](https://docs.openbox.ai/developer-guide/deep-agents/configuration.md): All Deep Agents SDK configuration options
    - [Error Handling](https://docs.openbox.ai/developer-guide/deep-agents/error-handling.md): Error codes and recovery patterns for the Deep Agents SDK
    - [Deep Agents Integration Guide (Python)](https://docs.openbox.ai/developer-guide/deep-agents/integration-walkthrough.md): Python-specific Deep Agents integration guide
    - [Extending the Demo Agent](https://docs.openbox.ai/developer-guide/deep-agents/extending-the-demo-agent.md): Customizing the Deep Agents demo for your use case
    - [Demo Architecture Reference](https://docs.openbox.ai/developer-guide/deep-agents/demo-architecture.md): How the Deep Agents demo is structured
    - [Troubleshooting](https://docs.openbox.ai/developer-guide/deep-agents/troubleshooting.md): Common issues and fixes for the Deep Agents SDK
  - [LangChain SDK (TypeScript)](https://docs.openbox.ai/developer-guide/langchain.md): LangChain TypeScript SDK reference and architecture
  - [LangGraph SDK (Python)](https://docs.openbox.ai/developer-guide/langgraph.md): LangGraph Python SDK reference and architecture
    - [Configuration](https://docs.openbox.ai/developer-guide/langgraph/configuration.md): All LangGraph SDK configuration options
    - [Error Handling](https://docs.openbox.ai/developer-guide/langgraph/error-handling.md): Error codes and recovery patterns for the LangGraph SDK
  - [Mastra SDK (TypeScript)](https://docs.openbox.ai/developer-guide/mastra.md): Mastra SDK reference and guide set
    - [Configuration](https://docs.openbox.ai/developer-guide/mastra/configuration.md): Mastra SDK configuration reference
    - [Error Handling](https://docs.openbox.ai/developer-guide/mastra/error-handling.md): Mastra SDK error handling and runtime recovery patterns
    - [Integration Walkthrough](https://docs.openbox.ai/developer-guide/mastra/integration-walkthrough.md): Mastra-specific integration walkthrough
    - [Event Model](https://docs.openbox.ai/developer-guide/mastra/event-model.md): Mastra SDK event model and payload guidance
    - [Approvals and Guardrails](https://docs.openbox.ai/developer-guide/mastra/approvals-and-guardrails.md): Mastra SDK approvals and guardrails behavior
    - [Telemetry](https://docs.openbox.ai/developer-guide/mastra/telemetry.md): Mastra SDK telemetry capture and runtime behavior
    - [Troubleshooting](https://docs.openbox.ai/developer-guide/mastra/troubleshooting.md): Mastra SDK troubleshooting guide
  - [n8n Developer Guide](https://docs.openbox.ai/developer-guide/n8n.md): n8n SDK integration and developer resources (coming soon)
  - [OpenClaw Plugin](https://docs.openbox.ai/developer-guide/openclaw.md): OpenClaw governance plugin reference and overview (coming soon)
  - [Temporal Plugin (Python)](https://docs.openbox.ai/developer-guide/temporal-python/sdk-reference.md): Full plugin API reference
    - [Configuration](https://docs.openbox.ai/developer-guide/temporal-python/configuration.md): All plugin configuration options
    - [Error Handling](https://docs.openbox.ai/developer-guide/temporal-python/error-handling.md): Error codes and recovery patterns
    - [Temporal Integration Guide (Python)](https://docs.openbox.ai/developer-guide/temporal-python/integration-walkthrough.md): Python-specific Temporal integration guide
    - [Extending the Demo Agent](https://docs.openbox.ai/developer-guide/temporal-python/customizing-the-demo.md): Customizing the demo for your use case
    - [Demo Architecture Reference](https://docs.openbox.ai/developer-guide/temporal-python/demo-architecture.md): How the demo agent is structured
    - [Troubleshooting](https://docs.openbox.ai/developer-guide/temporal-python/troubleshooting.md): Common issues and fixes
  - [Event Types](https://docs.openbox.ai/developer-guide/event-types.md): Reference for all emitted event types
  - [Working with llms.txt](https://docs.openbox.ai/developer-guide/llms-txt.md): LLM-optimized plain text documentation files

## Dashboard
- [Dashboard](https://docs.openbox.ai/dashboard.md): Trust overview and organization-wide monitoring
  - [Agents](https://docs.openbox.ai/dashboard/agents.md): Managing agents in the dashboard
    - [Registering Agents](https://docs.openbox.ai/dashboard/agents/registering-agents.md): How to register a new agent
    - [Agent Settings](https://docs.openbox.ai/dashboard/agents/agent-settings.md): Configure agent details and risk profile
  - [Trust Overview](https://docs.openbox.ai/dashboard/trust-overview.md): Aggregate trust view across all agents
  - [Alerts](https://docs.openbox.ai/dashboard/alerts.md): Configuring and responding to alerts

## Administration
- [Administration](https://docs.openbox.ai/administration.md): Organization management and compliance overview
  - [Organization](https://docs.openbox.ai/administration/organization.md): Managing your OpenBox organization
  - [Compliance & Audit](https://docs.openbox.ai/administration/compliance-and-audit.md): Compliance tooling and audit support
  - [Attestation & Cryptographic Proof](https://docs.openbox.ai/administration/attestation-and-cryptographic-proof.md): Tamper-evident cryptographic audit trails
  - [Audit Log](https://docs.openbox.ai/administration/organization-audit-log.md): Full org-level audit log reference