Run a self-hosted, sandboxed software factory
One developer's build log of an almost fully self-hosted, sandboxed agentic pipeline for producing software.
Done with a custom-built or unnamed agent
- What they did
- The author put Hermes, an agent using Codex, on a spare eBay PC with no inbound internet access. The box ran Coolify, Forgejo, self-hosted Firecrawl and Tailscale. One prompt asked for a calorie-tracking SvelteKit app. The agent created the repo, wrote the code and tests, fixed CI failures, and deployed the app with its own Postgres.
- How it went
- It reached a deployed app with no further prompts. One CSRF bug turned up on first use, and a single follow-up prompt got it diagnosed, fixed, covered by regression tests and redeployed.
- Worth knowing
- The only specific ongoing cost is a £20 Codex subscription. The sandbox is not harmless: the agent can still wipe the box and misuse any keys you give it.
Try it yourself with Claude Code
Help me design a sandboxed pipeline where coding agents build [project idea] inside Docker containers with no access to my personal files or credentials. Write the container setup, a task queue folder, and a script that runs one agent on one task and saves the result as a branch. Finish when I can run one example task end to end, and show me the plan before running anything that touches the network.
2 more accounts of this
Discussion on HN · Aug 21, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
- Claude
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
- Custom agent
Catch cloud outage risks before they happen
An autonomous ReAct agent that queries real data to stop cloud outages before they occur, built for the Sanity Challenge.
Hand narrow code changes to Devin for pull requests
A team used Devin for a month on small fixes like chart formatting and API edge cases, with tests and PRs; a complex full-stack task went poorly.
Migrate toolchain, architecture and site design with Claude Code
A developer had Claude Code switch a monorepo to oxlint/oxfmt, restructure the architecture and redesign a site, validating in a loop; the redesign took days instead of weeks.
Build and deploy a Game of Life simulation site
In a vendor launch demo, Devin built an interactive Game of Life website, added requested features step by step, and deployed it to Netlify.
Resolve a Slack-reported issue with a coding agent
A Codex agent resolved an issue passed to it in about 40 minutes, and an ops agent verified the fix back in Slack.