Real AI agent use cases, with sources and setup prompts

Use Claude Code, Codex and Gemini from one self-hosted assistant app

Conch is an open-source (MIT) self-hosted assistant that connects the plans and keys you already have, such as Claude Code, Codex, Copilot, Gemini and Ollama, and switches models without losing the thread. It works on web, desktop, phone and Telegram and stores everything in ~/.conch.

$17/mo30 minutesIntermediateSource linked

Source

@DanKornas on X · 2026-10-20

Written in our own words. Credit to the original author. Link checked 2026-10-22.

What they did

Conch is an open-source (MIT) self-hosted assistant that connects the plans and keys you already have, such as Claude Code, Codex, Copilot, Gemini and Ollama, and switches models without losing the thread. It works on web, desktop, phone and Telegram and stores everything in ~/.conch.

Result (as claimed)

One local-first interface for every provider.

Tools they used

ConchClaude CodeOpenAI CodexGitHub CopilotGemini CLIOllamaTelegram

Cost: Claude Code: from $17/mo; OpenAI Codex: free plan, paid from $8/mo; GitHub Copilot: free plan, paid from $10/mo.

Set it up

  1. Pick a contained repo or task

    Start on a branch or side project where mistakes are cheap.

  2. Install and configure

    Set up Conch, Claude Code, OpenAI Codex, GitHub Copilot, Gemini CLI, Ollama, Telegram. Read what it can run on your machine and limit permissions where possible.

  3. Run it on a real task

    Give it a well-scoped issue and let it work. Review the diff like any pull request.

  4. Add guardrails

    Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.

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: Use Claude Code, Codex and Gemini from one self-hosted assistant app
What the original author did: Conch is an open-source (MIT) self-hosted assistant that connects the plans and keys you already have, such as Claude Code, Codex, Copilot, Gemini and Ollama, and switches models without losing the thread. It works on web, desktop, phone and Telegram and stores everything in ~/.conch.
Reported result (as claimed by the author): One local-first interface for every provider.
Source: https://x.com/DanKornas/status/2112624736085700841
Tools they used: Conch, Claude Code, OpenAI Codex, GitHub Copilot, Gemini CLI, Ollama, Telegram
Category: Dev & ops

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 vibe code an app with Claude Code · How to run Claude Code and Codex in a desktop app (T3 Code, Codex app, Claude Desktop) · How to use Claude Code and Codex together · How to self-host AI agents on a Raspberry Pi, Mac mini or homelab

Related use cases