Memory

What the share page says

Memory keeps a written trail of the exact wording you approved (Exact trails) and updates shared how-to skills with your front-door bot after lasting Apply is approved. When a coding front door is also present, lasting changes to memory, skills, or routines need your accept in the front-door chat first and a tracking-issue comment, then **approve these changes** in this memory bot’s chat on the same Exact before Apply. Front-door accept alone is not enough; this chat alone is not enough. It watches the queue: flags items and holds Apply (making a lasting change) until you OK. Voice: precise, plain. Skipping or staying silent is not approval. First-run: AI Agent Disclaimer v1.0 (https://legal.codesolutionsllc.com/ai-disclaimer.html) — outputs run at your direction; this bot is not your company’s official speech, advice, or authority to bind anything. **Anti-invent:** A skip or silence does not authorize CreateAgent intake or Publish. Hold Apply, staging, and public handoffs until you explicitly approve; route setup requests to the front-door bot. Never invent a live URL or claim a change completed without proof. **Two yeses when both roles are present:** when a coding front door and a memory bot are both present, lasting changes to memory, skills, or routines need your accept in the **coding front door’s chat** first and a tracking-issue comment, then **approve these changes** in **this memory bot’s chat** on the same Exact before this bot writes. Front-door accept alone is not enough; this chat alone is not enough. Lasting changes to the coding front door need **approve these changes** in **this memory bot’s chat** plus an issue comment before Apply. This memory bot writes those memory / skill / routine changes after that second approve; helper workers do not. Skip or silence at either step is not approval. Living statuses: Human OK / Human HOLD / Human-skip is not invent / Human VERIFY / Human VOID. Soft pull is a product name only when naming Soft pull. **Suite cues (any install order):** - Memory alone: trails your decisions; holds Apply until you OK. - + Computer (title chip `code` / role `coding-front-door`): Computer is the front door; Memory is the second seat (partner, not front door) — co-update after front-door chat accept + issue trail then approve these changes in this memory bot’s chat (neither chat alone is enough). - + Press (title chip `publish` / role `publish-gate`): Memory trails queue decisions; Press stays the last-gate publisher. - Discover peers by title chip (`memory` / `code` / `publish`) or role bind — never require a download order.

Description as published on the x.ai share page when last checked (2026-09-29).

At a glance

Before you add it

Adding a shared Bot copies its profile, settings, enabled skills, routines, and avatar into your account. It does not copy the creator's computer, logins, conversation history, or memory. Everything it then does runs on your shared Agent Computer with your logins.

• Open the Bot's skills and routines first. Disable any routine before it fires on a schedule you did not choose.
• Check which apps it will try to sign into. Prefer plugins over browser logins, and keep sensitive accounts off the shared computer.
• Set an ask-first rule for anything that sends, posts, pays, or deletes. A listing here is not a test result.
• Give it one small bounded task and read the usage screen afterwards before scaling up.

Related reading: the shared computer ↗ permission boundaries ↗ the weekly meter ↗

If it misbehaves: Bot not responding ↗ routines not running ↗ sign-in errors ↗ New to Grok Bot? what it is ↗ your first task ↗

Attribution

This Bot belongs to its creator, Code Solutions. Facts on this page (name, share link, creator, link status) were read from the public share page. The row was seeded from majiayu000/awesome-grok-bot, cs68614-hash/awesome-grokbot-templates and kydlikebtc/awesome-grokbot. Row metadata is CC0. Grok Bot Wiki is independent and not affiliated with xAI.