Panella docs

Rendered from the repository's own markdown — the repo is the single source of truth.

• Quickstart — panella up to first approved memory — one person, one box, ~15 minutes
• Self-hosting — configuration and Docker topology
• Governance — the approval and audit model
• Security — security posture and reporting
• Team recipe — one governed box for a small Claude Code team — install, teammate on-ramp, daily approval rhythm, offboarding
• Operator console — flag-gated approvals, search, audit, and stats in the browser
• Upgrade — backup, upgrade, rollback
• Tenancy — multi-tenant boundaries
• Agent install guide — install and onboard a box end-to-end (for AI agents; raw file at /llms-install.md)
• How Panella compares — the two branches of agent memory and where Panella stands — category-factual, no vendor named

For agents: the agent install guide is also served raw at /llms-install.md, and /llms.txt indexes everything.