Whitzard
EN中文ConsoleJoin the waitlist

AGENTGUARD ENTERPRISE

Runtime security for AI agents

Apply security policies before and after model inference and tool calls, with sanitization, restricted execution, approval, or blocking.

Join the waitlistView Community Edition ↗
PROTECTED OBJECTSCover the complete context of agent action
  • Agents and subagents
  • Identity and delegation
  • Data and memory
  • Tools and MCP
  • External action and production systems
AgentGuard Community policy configuration interface
AgentGuard Community · Policy configuration and runtime control
ENTERPRISEAgentGuard Enterprise
OPEN SOURCEAgentGuard Community
FRAMEWORKS

LangChainMicrosoft AutoGenOpenAI Agents SDKLangGraphLlamaIndexDifyOpenClaw

CONTROL POINTSLLM · Tool · Memory
DEPLOYMENTInside the enterprise boundary

COMMUNITY EDITION

Policy, approval, and audit

See runtime traffic, policy configuration, approval, and audit. Enterprise adds deployment and integration support.

AgentGuard Community runtime monitoring interface
Community Edition interface

Runtime traffic and decisions

Inspect tool calls, policy matches, and decisions by session.

View original ↗

USE CASES

Protect agents in business workflows

Office productivity

Knowledge search, document processing, email, and collaboration.

Apply data and access boundaries as information is retrieved and shared, reducing the risk of sensitive data exposure and unauthorized access.

Explore use case →

Development & operations

Code changes, command execution, environment configuration, and resource management.

Constrain high-risk commands and production changes so automated operations remain controlled and traceable.

Explore use case →

Computer-use agents

Navigation, data entry, and business tasks in browsers, desktop software, and mobile apps.

Set boundaries for autonomous interface actions to reduce mistakes, unauthorized operations, and unintended submissions.

Explore use case →

AI workflows

Knowledge-base Q&A, tool orchestration, and cross-system processes on workflow platforms such as Dify.

Apply security requirements to workflow nodes and cross-system calls, supporting consistent management and investigation.

Explore use case →

Action boundary control

Configure policies and retain audit evidence across agent interactions with models, tools, and data.

01

Control points

Apply security checks before and after model and tool execution, using task context to identify the interaction boundaries that need controls.

02

Policy configuration

Configure security rules and responses around business requirements, with constraints on model output, tool use, and data flows.

03

Audit records

Review execution traces, rule matches, and control decisions to support investigation and policy review.

EDITIONS

Community and Enterprise editions

Community provides the open runtime-security foundation. Enterprise supports organization-wide deployment and continuous security operations.

Open source · GPLv3

AgentGuard Community

A self-managed edition for developers and researchers.

  • Public framework adapters
  • Four runtime hooks
  • DSL policy rules
  • Visual configuration
  • Runtime audit
  • Plugin extensions
View Community Edition ↗
Enterprise deployment

AgentGuard Enterprise

For organization-wide deployment, integration, and continuous security operations.

  • Private deployment support
  • Central policy and audit integration
  • Custom adapters
  • Custom policies and safety models
  • Continuous validation and technical support
Join the waitlist

INTEGRATION & DEPLOYMENT

Controls within the trust boundary

Connect through hooks, sidecars, or gateways. Keep policy and evidence private.

ENTERPRISE TRUST BOUNDARYSECURITY CONTROL LAYER
Policy, traces, and evidence stay in your environment
01AGENT WORKLOADS & EXECUTION
Agent frameworksSDK · Sidecar · Gateway
AGENTGUARDAgentGuard Runtime

Continuous control before and after model and tool execution

  1. 01Pre-execution checks
  2. 02Runtime protection
  3. 03Post-execution audit
Models · Tools · MCP · DataPrivate Control Plane
01Application embedded

Hooks preserve full runtime context.

02Infrastructure enforced

Gateways centralize tool and data control.

03Privately operated

Keep policy, traces, and evidence private.

WORKS WITH YOUR SECURITY STACK

Add agent-aware runtime context

AgentGuard complements existing security systems with context for the full agent action

IAMStatic identity and permissionsTask context, delegation chain, and one-time grants
DLPContent and egress channelsDerived-data lineage and multi-step propagation
API GatewayIndividual requestsThe model, tool, and task trace before each request
SIEMEvents and logsDecision evidence, payload change, and business outcome

VERIFIABLE EVIDENCE

Code, models, and research

AgentGuard Community

The open runtime-security foundation for developers and researchers.

Community · GitHub →

Safety models

Models for reasoning alignment, intent analysis, and reasoning safety.

Ecosystem →

NUWA research

Frontier risk, agent safety, and AI control.

Research →

Integrate runtime security

Share your stack, critical permissions, and deployment constraints through the product waitlist.

  1. Map one real agent workflow
  2. Mark identity, data, and action boundaries
  3. Discuss policy configuration and control requirements
  4. Review actual product interfaces and audit records
  5. Discuss integration and private deployment
Join the waitlistCommunity Edition ↗