Integrations

Security for Every AI Framework

Rune plugs into the frameworks you already use. Add runtime security to your AI agents in minutes — scan every input, output, and tool call for prompt injection, data exfiltration, and policy violations.

Supported Frameworks and Why They Need Runtime Security

Rune provides native integrations for the most popular AI agent frameworks. Each integration hooks into the framework's specific middleware, callback, or interceptor system — not a generic wrapper. This means Rune can scan tool call parameters, inter-agent messages, retrieved documents, and streaming responses at the framework level, catching threats that generic solutions miss.

If your framework isn't listed, Rune's generic Shield class works with any Python-based agent. Wrap your input/output processing and get the same multi-layer scanning. Native integrations just make the setup easier and the coverage deeper.

LangChain

Middleware-native security for LangChain and LangGraph agents

pip install runesec[langchain]
RAG PoisoningTool Call Manipulation
Learn more
OpenAI

Transparent security wrapper for the OpenAI Python SDK

pip install runesec[openai]
Function Parameter InjectionAssistants API Abuse
Learn more
Anthropic

Drop-in security wrapper for the Anthropic Python SDK

pip install runesec[anthropic]
Long-Context InjectionTool Use Block Manipulation
Learn more
CrewAI

Two-layer security for multi-agent CrewAI workflows

pip install runesec[crewai]
Inter-Agent EscalationTool Chain Attacks
Learn more
MCP

Security proxy for Model Context Protocol servers

pip install runesec[mcp]
Malicious MCP ServersServer Integrity Compromise
Learn more
OpenClaw

Native interceptor-based security for OpenClaw agents

openclaw plugins install @runesec/openclaw
Malicious ClawHub SkillsUnrestricted System Access
Learn more
PagerDuty

Route agent security incidents to your on-call team

Configure in Rune Dashboard → Settings → Notifications
Unattended Critical AlertsDelayed Incident Response
Learn more
Datadog

Unified observability for agent security and infrastructure

Configure in Rune Dashboard → Settings → Notifications
Blind Spots in ObservabilityUncorrelated Incidents
Learn more
Splunk

Enterprise SIEM integration for agent security events

Configure in Rune Dashboard → Settings → Notifications
SOC Blind SpotsCompliance Gaps
Learn more
Sentry

Track blocked agent actions as Sentry errors

npm install @sentry/node @runesec/sdk
Silent Security FailuresDebugging Blind Spots
Learn more

Don't see your framework? Rune's generic Shield class works with any Python agent. See the SDK docs

Frequently Asked Questions

How long does integration take?

Most integrations take under 5 minutes. Install the SDK with pip install runesec, import the framework-specific integration (e.g., ShieldMiddleware for LangChain), and wrap your existing agent. No code refactoring required — Rune hooks into your framework's existing middleware or callback system.

Does Rune work with custom or proprietary frameworks?

Yes. Rune's generic Shield class works with any Python-based agent. Call shield.scan_input() before sending data to your LLM and shield.scan_output() before returning results to the user. The framework-specific integrations automate this wrapping, but the core scanning is framework-agnostic.

Does integration affect my agent's performance?

Rune's L1 pattern scanning adds under 5ms of latency. L2 semantic scanning adds 10-20ms. Both run locally with no external API calls. L3 LLM-based judgment is optional and can run asynchronously (non-blocking). Event shipping to the dashboard is always asynchronous and never blocks your agent's response.

Can I use Rune with multiple frameworks in the same project?

Yes. Create one Shield instance and use it across multiple framework integrations. For example, if you have a LangChain RAG pipeline feeding into a CrewAI multi-agent system, you can wrap both with the same Shield instance and see unified monitoring in the dashboard.

Add runtime security in under 5 minutes

Pick your framework, install the SDK, and wrap your client. Every input, output, and tool call is scanned automatically.

Start Free — 10K Events/Month
AI Agent Security Integrations — Rune | Rune