THREAT OPS › Threat News › Sage: AI for Assumed-Breach Operations, Built Into Mythic
Sage: AI for Assumed-Breach Operations, Built Into Mythic
<p class="wp-block-paragraph"><em><strong>TL;DR:</strong> Sage is an open-source AI assistant that lives inside Mythic. You tell it what you’re trying to accomplish, it works out the commands across whichever Mythic agents you have, and every action waits for your approval before it reaches a target. It keeps the operation’s memory in BloodHound and in an Engagement State Ledger, where
MITRE ATT&CK techniques
- CredentialsT1589.001
Indicators of compromise
- https://docs.mythicsage.ai/understand/authority-modesurl
- https://arxiv.org/abs/2308.06782url
- https://arxiv.org/abs/2501.16466url
- https://arxiv.org/abs/2307.03172url
- https://docs.mythicsage.ai/guides/engagement-ledgerurl
- https://docs.mythicsage.aiurl
- https://docs.mythicsage.ai/guides/bloodhoundurl
- https://platform.openai.com/docs/api-referenceurl
- https://docs.mythicsage.ai/guides/chat-configurl
- https://docs.mythicsage.ai/reference/tools-and-capabilitiesurl
- https://phoenix.arize.comurl
- https://docs.mythicsage.ai/configuration/observabilityurl
- https://docs.mythicsage.ai/configuration/runtime-stateurl
- https://docs.mythicsage.ai/guides/findings-watcherurl
- https://docs.mythicsage.ai/guides/mcp-serversurl
- https://docs.mythicsage.ai/reference/slash-commandsurl
- https://docs.mythicsage.ai/understand/how-sage-worksurl
- https://docs.mythicsage.ai/understand/limitationsurl
- https://docs.mythicsage.ai/quickstarturl