Local model servers
Guard’s inventory records local model servers such as Ollama, LM Studio and vLLM: their version, listening ports and the models they hold.
Rune Guard docs →Who it’s for
Open labs, local models, and agents everywhere.
Research groups mix local models, notebooks, coding agents and borrowed tools. Guard shows what is installed and what it reaches; Rune Box gives agents a governed place to work, for free.
What worries you
And what Runewrd Labs does about it.
Shadow AI across many devices
Guard discovers AI tools missing from the catalog and records their approval state.
Shadow AI →Agents that run experiments
Rune Box is open source: policy, approvals, isolated sandboxes and a signed, verifiable audit trail around any agent.
Rune Box docs →Deploying it
How it fits
- Community: Rune Box is free and open source.
- Hosted Guard Cloud processes telemetry in the EU.
Honest limitations
What to know first
- Runeward Labs holds no security certifications. Framework mappings in findings are candidate mappings for triage, not compliance evidence.
- Rune Guard is in early access, and what it covers differs by platform and harness: see the known limits before relying on a signal.
Your agents already have access. Ward off the risks.
Join Guard early access for your team, or run the free local scan today. Agents in automation too? Add the open-source Rune Box.