# Building a Personal Assistant Orchestrator with Claude Code and Headless Sub-Agents

DevFeed: [Building a Personal Assistant Orchestrator with Claude Code and Headless Sub-Agents](<https://devfeed.tech/articles/personal-assistant-without-openclaw-or-hermes-just-one-prompt-25427.md>)

Original publisher: [Read original article](<https://jonnyzzz.com/blog/2026/07/19/personal-assistant-agent/>)

Author: Eugene Petrenko

Published: 2026-07-19T00:00:00Z

Content type: article

Language: en

Sources: [Eugene Petrenko](<https://devfeed.tech/sources/eugene-petrenko.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Code](<https://devfeed.tech/topics/code.md>), [Processes](<https://devfeed.tech/topics/processes.md>), [Git](<https://devfeed.tech/topics/git.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [OpenClaw](<https://devfeed.tech/topics/openclaw.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [eugene-petrenko](<https://devfeed.tech/tags/eugene-petrenko.md>), [git](<https://devfeed.tech/tags/git.md>), [hermes-agent](<https://devfeed.tech/tags/hermes-agent.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [jonnyzzz](<https://devfeed.tech/tags/jonnyzzz.md>), [openclaw](<https://devfeed.tech/tags/openclaw.md>), [process](<https://devfeed.tech/tags/process.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [self-improvement](<https://devfeed.tech/tags/self-improvement.md>), [slack](<https://devfeed.tech/tags/slack.md>), [tag-41199d53f463](<https://devfeed.tech/tags/tag-41199d53f463.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

## AI overview

The article describes building a personal-assistant orchestrator from a prompt in an interactive Claude Code session. It routes requests from Slack and Telegram, assigns each task to a fresh headless sub-agent process, and uses files, process boundaries, and git to manage work and recovery. The author also compares the approach with OpenClaw and Hermes.

## Source excerpt

In one afternoon -- one pasted prompt, included below -- we turned an interactive Claude Code session into a personal-assistant orchestrator: channels in, a fresh headless sub-agent per request, an inbox loop that delivers finished work before taking new work, and a three-lens quorum that reviews and ships its own process fixes. By day two it was also babysitting the machine's other AI Agent consoles through a guarded keystroke path. No daemon, no webhooks, no database -- jsonl files, blocking CLIs, and git as the deployment mechanism -- and a hands-on comparison against OpenClaw and Hermes.