Self-host an AI teammate with local models and approval before risky steps
He built LocalCrew, a self-hosted assistant inspired by Grok Bot that runs on local models, keeps persistent tasks, uses browser tools and asks for human approval before sensitive actions.
Source
@ibuildstufff on X · 2026-10-20
Written in our own words. Credit to the original author. Link checked 2026-10-20.
What they did
He built LocalCrew, a self-hosted assistant inspired by Grok Bot that runs on local models, keeps persistent tasks, uses browser tools and asks for human approval before sensitive actions.
Result (as claimed)
Released as a project page; early stage.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Map the task
Write the trigger, the inputs, the decisions and the output. Note which steps need a human yes.
Connect the tools
Set up Ollama with the narrowest permissions that work. Use a test account or sandbox first.
Build the workflow
Create the steps in order. Add an approval step before anything sends, pays or deletes.
Run it on real but low-stakes data
Run a few times, read every output, and fix prompts or rules that misfire.
Schedule and monitor
Turn on the schedule or trigger, and add a daily summary or alert so you notice failures.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Self-host an AI teammate with local models and approval before risky steps What the original author did: He built LocalCrew, a self-hosted assistant inspired by Grok Bot that runs on local models, keeps persistent tasks, uses browser tools and asks for human approval before sensitive actions. Reported result (as claimed by the author): Released as a project page; early stage. Source: https://x.com/ibuildstufff/status/2112490772469866660 Tools they used: Ollama Category: Automation & business Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Self-host an AI teammate with local models and approval before risky steps What the original author did: He built LocalCrew, a self-hosted assistant inspired by Grok Bot that runs on local models, keeps persistent tasks, uses browser tools and asks for human approval before sensitive actions. Reported result (as claimed by the author): Released as a project page; early stage. Source: https://x.com/ibuildstufff/status/2112490772469866660 Tools they used: Ollama Category: Automation & business Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Self-host an AI teammate with local models and approval before risky steps What the original author did: He built LocalCrew, a self-hosted assistant inspired by Grok Bot that runs on local models, keeps persistent tasks, uses browser tools and asks for human approval before sensitive actions. Reported result (as claimed by the author): Released as a project page; early stage. Source: https://x.com/ibuildstufff/status/2112490772469866660 Tools they used: Ollama Category: Automation & business Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to self-host AI agents on a Raspberry Pi, Mac mini or homelab · How to use AI agents for Linux, servers and homelabs · How to make AI agents ask for approval before they act · How to set up Grok Bot agents for real work
Related use cases
Put Claude Code, Codex and a local model in one group chat you control from your phone
RAPR AI puts Claude Code, Codex and Ollama in one group chat on your own machine, controlled from your browser, Telegram or WhatsApp.
Run Claude Code against local Ollama or LM Studio models
Built ccl so the official Claude Code CLI talks to local models via Ollama, LM Studio or Hugging Face GGUF at zero API cost.
Run a local AI pentesting agent on a smartphone
Built Nightcrawler, a local AI pentesting agent that runs on a smartphone.
Add local-first memory to any LLM with Mnemo
Built Mnemo, a local-first AI memory layer for any LLM using Rust, SQLite and petgraph.