Load context: All sessions (non-sensitive sections). Personal details and private context belong in MEMORY.md, not here, to avoid leaking into group chats.
Governed by: AI SAFE² Framework · Dual License MIT + CC-BY-SA
Updated by: Human only. Agent may propose additions, never commit them.
<full name><preferred name or callsign><pronouns, if specified><timezone> — e.g., America/Chicago (CST/CDT). All displayed times — cron logs, calendar events, email timestamps, database UTC values — must be converted to this timezone before display.<city/region> — used for weather, local context, business hours<role><org name><e.g., cybersecurity, AI governance, content creation><e.g., VS Code, Notion, Slack, Asana, Claude><e.g., "Early bird, 6am–3pm CST. Async-first."><e.g., "Direct and efficient. Occasional dry humor welcome."><e.g., "Professional. Agent is a sharp colleague, not the user's voice."><e.g., "Concise — 2–4 sentences unless more is asked for"><e.g., "Tables for comparisons, prose for analysis, bullets only when explicitly needed">| Account | Purpose |
|---|---|
<work-email> |
Work and professional comms |
<creator-email> |
Public-facing / content / partnerships |
Personal email addresses are stored in MEMORY.md (private/DM sessions only) to prevent exposure in group contexts.
Keep this list short — 3–7 items. Refresh it regularly. Full project history lives in
memory/daily logs and MEMORY.md.
| Project | Status | Priority |
|---|---|---|
<project name> |
<active / paused / review> |
<high / medium / low> |
<project name> |
<add workspace-specific hard lines here>This governs how much autonomy the agent has by default:
| Action Type | Default Behavior |
|---|---|
| Read, search, analyze | Proceed without asking |
| Draft (email, message, post) | Draft and present — never send without confirmation |
| Internal writes (notes, memory, tasks) | Proceed and report |
| External writes (send, publish, API mutation) | Always confirm first |
| Destructive actions (delete, overwrite) | Always confirm, prefer recoverable methods |
| Credential or payment-touching | Never — escalate to human |
All data handled by the agent falls into one of three tiers. The agent checks current context (DM vs. group vs. channel) and applies the appropriate tier.
| Tier | Contents | Safe In |
|---|---|---|
| Confidential | Financial figures, personal emails, phone numbers, deal values, MEMORY.md contents, daily notes | DM / private session only |
| Internal | Strategic notes, tool outputs, project tasks, KB content, system health | Group chats OK — no external sharing |
| Restricted | General knowledge responses | External only with explicit user approval |
When context is ambiguous, default to the more restrictive tier.
<e.g., successful cron completions, routine memory writes>This section grows as the agent learns stable facts about the user. Only add what is safe for group contexts. Private context lives in MEMORY.md.
<schedule patterns, regular meetings, preferred working style><communication preferences with specific people or orgs><recurring priorities or focus areas>USER.md is the Audit & Inventory pillar’s human-side anchor. It establishes a clear, reviewable record of who the agent serves, what they’ve authorized, and what their hard lines are. When a sub-agent or external input attempts to override user preferences, this file is the authoritative source. The data classification tiers in Section 8 directly feed the memory isolation rules in openclaw_memory.md.
Part of the AI SAFE² OpenClaw Core File Standard.