Chinese personal swarms: one qualified account and one source-backed mechanism
Reviewed September6,2026 UTC

Just Jason account
https://junxinzhang.com/openclaw-shrimp-farming-3-agents-automated-loop/
HTTP200; HTML self-dates publication/modification February25,2026. It describes an orchestrator, coding assistant Winnie and writing assistant Amy, with a claimed VoiceTranslation bug-fix PR. Human review/merge remains explicit. Crucially, closing next steps include configuring the cron monitor and testing the Winnie-to-Amy handoff, despite earlier complete-automation language. Treat the cross-agent loop as incompletely substantiated, not verified production autonomy. No specific PR URL is linked in this article.

The related translation article links the author's GitHub profile but not the project repository:
https://junxinzhang.com/macos-realtime-translation-for-teams-standard/
Public API lists85 repositories in the single returned100-item page; no repository name contains voice or translat. This does not exclude a differently named/private/deleted repository. Two tempting names resolve differently: junxinzhang/openclaw is a fork of openclaw/openclaw; junxinzhang/swarm is a fork of docker-archive/classicswarm, last pushed2018. The latter is Docker clustering, not this AI team. No personal API proxy or private logs accessed.

Huashu source
https://github.com/alchaincyf/huashu-skills/tree/023408a49191270c69508390d77d0c8197828d80/huashu-agent-swarm
Nontruncated GitHub tree inspected. Four source downloads match Git blob SHA1: SKILL.md, scripts/start_swarm.sh, scripts/agent_loop.sh, references/agent-prompt-template.md. Read as data only; never installed/executed.

Launcher creates separate Git worktrees and tmux panes, default8. Loop invokes Claude CLI, defaults claude-opus-4-6, records each session, and attempts Git synchronization/push. Prompt asks workers to coordinate through task-claim files and Git history. This is implemented orchestration machinery; no actual run archive appears in the inspected skill subtree, which contains documentation/templates/scripts. No claim about every other repository directory or historical revision follows from that scoped check.

Useful search fingerprints from the pinned source:
- agent_logs/agent_<ID>_session_<COUNT>_<YYYYMMDD_HHMMSS>.log
- current_tasks/<task_name>.lock
- commit-message pattern: Agent-<ID>: claim task <task_name>
- commit-message pattern: Agent-<ID>: complete task <task_name>
- HUMAN_INPUT.md and TASKS.md jointly with the above
Generic Agent-N or TASKS.md alone will be noisy. Public search returned catalog mirrors/translation, not an independently recovered run. A match would still require content and provenance review.

Conclusion
Chinese-language users have concrete swarm implementations, including Western-model orchestration. This does not identify a Chinese lab's escaped agents. Highest-value follow-up is matching these source fingerprints to real public work histories, rather than collecting further copied skill listings.

Preservation
262-private contains article/related-page HTML, public repository metadata, pinned Huashu tree and four checked source files, with SHA256SUMS. Public mirror is whitelisted observation metadata only. Current server reached all reviewed primary sources; no additional infrastructure needed for this pass.