Persistent Agent Teams With Herdr, Claude Code and Pi
Recreate always-on agent teams on your own VM: named peers that remember the project and talk.
About Persistent Agent Teams With Herdr, Claude Code and Pi
A hands-on walkthrough of running persistent agent teams on an always-on Linux VM with Herdr, first with Claude Code and then with Pi on a GitHub Copilot subscription. The author recreated the always-on, group-chat style of Grok Bot after its free quota ran out: named agents that know the project, remember past discussions and talk to each other.
Why it is worth reading: it covers setting up a team, organising agents into groups, and an honest section on what goes wrong (teams magnify failure modes). It ends with a gist of bootstrap scripts and TEAM_*.md boilerplates you can copy.
The author's own verdict: probably not higher accuracy than single-task sessions, but a way of working they like much more.
The facts
- Type
- Guides
- Tags
- AIAutomationDeveloper Tools
- Listed
- October 26, 2026
More Guides
See all →- Headless Content Marketing: A New (Old) Strategy for SearchAhrefs on pages written mainly for AI answers, why big brands are making them, and what it means.
- How to Publish Posts via the dev.to APIPublish to dev.to from a curl command or a Python script, front matter and images included.
- Building Better Agents Through End-to-End EvalsHow Ramp Stack grades a bookkeeping agent: messy synthetic worlds, rubrics and skill ablation.
- Can a Local LLM Replace Claude Code? The Benchmark Everyone Quotes Is the Wrong OneWhy SWE-bench misleads, and what actually breaks when a local model drives your coding agent.
- The September Cut Took 17% of My Claude Code Week. Subagents Took 48%455 sessions of logs show where a Claude Code week actually goes, and which saving tips work.