Your agents process untrusted input.
Rune makes that safe.

Prompt injection, data exfiltration, tool abuse — these attacks happen at runtime, not in your test suite. Rune scans every LLM input and tool call in real time. Open-source SDK, under 10ms overhead, 3 lines of code.

Free plan · 10K events/mo · No credit card required

agent.py
from rune import Shield

shield = Shield(api_key="rune_live_...")

# Wrap any tool call — inputs blocked,
# outputs scanned automatically
@shield.protect(agent_id="my-agent")
async def call_tool(name, params):
    return await agent.run(name, **params)

# Or scan manually:
result = shield.scan_input(user_message)
if result.blocked:
    print(f"Threat: {result.threat_type}")

# ✓ Inputs blocked before execution
# ✓ Outputs scanned for data leaks
# ✓ Anomalies flagged in real time

Install: pip install runesec

Lakera → Check Point. Protect AI → Palo Alto. Promptfoo → OpenAI. Rune is still independent.

<5ms latency52 detection patterns3 lines to integrate
Works withLangChain · OpenAI · Anthropic · CrewAI · MCP · OpenClaw

See what Rune catches

Paste any text and watch the scanner detect threats in real time. Same engine that protects your agents in production.

InputPattern scanning (client-side)
Scan Results

Scan results will appear here

Try:

One import. Full runtime protection.

Add Rune to your existing agent code. No refactoring, no new abstractions.

Known attacks blocked in under 5ms

Pattern-based rules catch prompt injections, data exfiltration, and command injection before your agent can act on them.

Novel attacks caught even when disguised

Semantic analysis detects obfuscated prompts, encoded payloads, and techniques that haven't been seen before — beyond what regex can catch.

Per-agent risk scores and real-time alerts

Know exactly what every agent is doing — and what Rune stopped it from doing. Event timelines, anomaly detection, and alert routing built in.

Your policies, enforced on every call

Define which tools each agent can call, with what arguments, under what conditions. YAML policies checked on every event, automatically.

Behavioral anomaly detection

Unusual call frequency, new tool combinations, sudden risk score spikes — Rune flags deviations from established agent patterns.

Start free. Scale when you're ready.

10K events on the free plan. Upgrade for more agents, deeper scanning, or longer retention. No surprise bills. No credit card to start.

Community

Free

Get started with up to 5 agents, free forever

Events/mo10,000
Agents5
ScanningL1 only
  • 10K events/mo
  • 5 agents
  • L1 regex scanning
  • 30-day retention
  • 3 policies
  • Email alerting
Create Free Account

Starter

$49/mo

For small teams shipping their first agents to production

Events/mo50,000
Agents25
ScanningL1 + L2
  • 50K events/mo
  • 25 agents
  • L1 + L2 scanning
  • 90-day retention
  • 10 policies
  • Email support
  • Email + Slack alerting
  • $0.80 per 1K overage events
Start 14-Day Trial

Pro

$149/mo

For teams running production agents with full scanning

Events/mo250,000
Agents100
ScanningL1 + L2 + L3
  • 250K events/mo
  • 100 agents
  • L1 + L2 + L3 scanning
  • 180-day retention
  • Unlimited policies
  • Priority email support
  • All alerting channels
  • $0.50 per 1K overage events
Start 14-Day Trial

Growth

$499/mo

For companies with high-volume agent deployments

Events/mo1,000,000
Agents500
ScanningAll layers
  • 1M events/mo
  • 500 agents
  • All scanning layers
  • 365-day retention
  • Unlimited policies
  • Slack + email support
  • All alerting channels
  • Audit log export
  • $0.30 per 1K overage events
Start 14-Day Trial

Pay As You Go

Usage-based pricing for unpredictable workloads

$1.00
per 1K scans
$10
monthly minimum
L1 + L2
scanning layers
Unlimited
agents

No included events — pay only for what you use. Includes 90 days retention.

All paid plans include overage pricing — never get cut off mid-month. Need higher limits or a custom contract? Contact us at hello@runesec.dev

Frequently asked questions

How long does integration take?

Under 10 minutes. Install the SDK, create a Shield with your API key, wrap your agent. Three lines of code for most frameworks.

Which agent frameworks do you support?

Rune works with OpenAI SDK, Anthropic SDK, CrewAI, LangChain, and MCP out of the box. The SDK is framework-agnostic — if your agent makes tool calls, Rune can intercept them.

Will Rune slow down my agents?

L1 scanning adds under 5ms per call using regex pattern matching. L2 semantic analysis adds under 30ms (Starter plan and above). L3 LLM-based analysis runs asynchronously so it doesn't block your agent (Pro plan and above).

Can I test policies before deploying them?

Yes. The policy editor includes a built-in test panel where you can simulate actions against your YAML policies and see the result before anything goes live.

What happens when Rune detects a threat?

For inputs: the tool call is blocked before it executes. For outputs: the response is flagged after execution and an alert is created. In both cases, an alert appears in your dashboard with the agent, event, triggering policy, and severity rating. You can route alerts to email, Slack, or webhooks.

Do I need to change my agent code?

No. Rune wraps your existing agent as middleware. Your logic, prompts, and tool definitions stay exactly the same.

What's the difference between L1, L2, and L3 scanning?

L1 uses regex pattern matching for known threats — fast and deterministic (all plans). L2 uses vector similarity to catch novel attacks that don't match known patterns (Starter+). L3 uses an LLM judge to evaluate ambiguous threats with full context (Pro+). Higher tiers auto-enable when you connect with a paid plan API key.

How does Rune work in CI/CD?

Run Rune in dry-run or monitor mode in your test suite. It scans agent interactions during integration tests and catches issues before they reach production — without blocking your pipeline.

Can I use this in staging before production?

Yes. Run Rune in monitor mode in staging to observe threats without blocking, then switch to enforce mode in production. You can configure different modes per environment.

How do you handle false positives?

L1 scanning is deterministic pattern matching — zero false positives on known attack patterns. L2 semantic analysis has a configurable confidence threshold you can tune. L3 LLM-based analysis creates alerts for human review rather than auto-blocking.

What data do you store?

Event metadata only — agent ID, threat type, severity, action taken, and timestamps. Content is scanned in transit and not persisted. We never train on customer data.

The last independent agent security platform.

Every competitor got acquired. We're still shipping for developers. Three lines of code. No enterprise sales call required.

Free plan. No credit card.

Rune — Runtime Security for AI Agents | Rune