Agent-shell: vendor-neutral chat with AI agents in Emacs
Built Agent-shell, vendor-neutral chat with AI agents in Emacs.
Source
xenodium on Hacker News · 2026-08-15 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-16.
What they did
Built Agent-shell, vendor-neutral chat with AI agents in Emacs.
Result (as claimed)
Launched publicly; shared on Show HN (28 points).
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up emacs. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
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: Agent-shell: vendor-neutral chat with AI agents in Emacs What the original author did: Built Agent-shell, vendor-neutral chat with AI agents in Emacs. Reported result (as claimed by the author): Launched publicly; shared on Show HN (28 points). Source: https://news.ycombinator.com/item?id=49309755 Tools they used: emacs 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.
You are helping me set up this AI use case end to end in Codex. Goal: Agent-shell: vendor-neutral chat with AI agents in Emacs What the original author did: Built Agent-shell, vendor-neutral chat with AI agents in Emacs. Reported result (as claimed by the author): Launched publicly; shared on Show HN (28 points). Source: https://news.ycombinator.com/item?id=49309755 Tools they used: emacs 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.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Agent-shell: vendor-neutral chat with AI agents in Emacs What the original author did: Built Agent-shell, vendor-neutral chat with AI agents in Emacs. Reported result (as claimed by the author): Launched publicly; shared on Show HN (28 points). Source: https://news.ycombinator.com/item?id=49309755 Tools they used: emacs 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.
Related use cases
Grafana agent observability for Hermes Agent
Shipped Grafana agent observability for Hermes Agent and shared it as a Show HN.
Let an agent draw on a TLDraw canvas while you talk
Built Agent Draw so an agent sketches on a TLDraw canvas while you talk through the idea.
Let an agent debug your app on a spare phone
Enable USB or Wi-Fi debugging on an old Android phone, connect it, and ask Hermes agent or Claude Code to test and debug your mobile app.
Self-host a sandbox for code your agent writes
Built Plimsoll, a self-hosted sandbox service for untrusted agent-authored code with isolation reporting.