# Sage

> Documentation for Sage, an AI operator for the Mythic command and control framework.

- [Sage](https://docs.mythicsage.ai/index.md): Sage is an AI operator that lives inside your Mythic C2: it reads your live operation, reasons like an analyst over the BloodHound attack graph, and drives real Mythic tasks.
- [Quickstart](https://docs.mythicsage.ai/quickstart.md): Install Sage into a running Mythic server and hold your first conversation.
- [How Sage works](https://docs.mythicsage.ai/understand/how-sage-works.md): The observe → model → select → execute → verify loop, the two execution paths, the specialist agent graph, and the engagement ledger that makes effects durable.
- [Authority modes](https://docs.mythicsage.ai/understand/authority-modes.md): What conversation, supervised, and auto mean, and exactly where the approval wall sits.
- [Security and data handling](https://docs.mythicsage.ai/understand/security-and-data-handling.md): The control-plane boundary, evidence rules, and what Sage does with your operation's data.
- [Limitations and validated configuration](https://docs.mythicsage.ai/understand/limitations.md): The configuration Sage's beta was live-validated against, what that does and does not establish, and the known limits.
- [Using Sage in chat](https://docs.mythicsage.ai/guides/using-chat.md): Working with a Sage chat channel: choosing a mode, approving guarded actions, and stopping a running agent.
- [Chat channel configuration](https://docs.mythicsage.ai/guides/chat-config.md): Creating a Sage chat channel: what each field in the New AI Chat dialog does, and how to keep credentials out of plaintext.
- [The engagement ledger](https://docs.mythicsage.ai/guides/engagement-ledger.md): Durable engagement state: the /state hop ledger, reconciling completed Mythic tasks, and what a proof envelope requires.
- [BloodHound](https://docs.mythicsage.ai/guides/bloodhound.md): Connect BloodHound CE to Sage: the graph Sage observes, reasons over, and plans against.
- [Connecting MCP servers](https://docs.mythicsage.ai/guides/mcp-servers.md): Attach any third-party MCP server to Sage, with an execution class, a tool policy, and the control-plane rule.
- [Custom TLS certificates](https://docs.mythicsage.ai/guides/custom-tls.md): Trust private CAs for model endpoints, MCP servers, and BloodHound, in addition to the public roots.
- [Background findings watcher](https://docs.mythicsage.ai/guides/findings-watcher.md): The Sage Watcher model: a locked, operation-wide watcher that polls Mythic's read streams and posts findings, without touching targets.
- [Troubleshooting](https://docs.mythicsage.ai/guides/troubleshooting.md): Symptoms you may hit while installing and running Sage, what each one means, and where the fix is documented.
- [Environment and configuration](https://docs.mythicsage.ai/configuration/environment.md): How Sage resolves settings: the first-non-empty chain, the deliberately tracked .env file, and model configuration.
- [Runtime state and resets](https://docs.mythicsage.ai/configuration/runtime-state.md): What Sage persists, where, what a restart does to your chats, and how to reset cleanly without losing history.
- [Observability](https://docs.mythicsage.ai/configuration/observability.md): Traces, token accounting, and telling the two execution paths apart, with the embedded Phoenix UI.
- [Tools and capabilities](https://docs.mythicsage.ai/reference/tools-and-capabilities.md): Sage's tool inventory: the read-only vs. guarded split, the generic capability layer, and the tool drop zone.
- [Slash commands](https://docs.mythicsage.ai/reference/slash-commands.md): Every command available in a Sage chat channel.
- [Release notes](https://docs.mythicsage.ai/reference/release-notes.md): What changed in each Sage release, adapted from the Sage changelog.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.