I passed through some evolution, from todo list with /clear + "take next task" prompt to cleaning most of the skills/plugins/claudemd, using centralized beads db, developing ask_human mcp on sqllite and creating lightweight python orchestrator with ui: https://github.com/sermakarevich/fleet.

My use cases are:

- centralized interface for spawning unrelated single tasks in parallel

- coding with spec driven development approach: https://github.com/sermakarevich/sddw - I can chain sdd workflow steps with beads --deps

- reviewing codebase and triggering many small tasks to be executed in parallel

Few articles:

- https://simonwillison.net/2025/Oct/5/parallel-coding-agents/

- https://zachwills.net/i-managed-a-swarm-of-20-ai-agents-for-a-week-here-are-the-8-rules-i-learned/

- https://juhache.substack.com/p/on-the-road-to-agent-swarms

How do you run agent swarm today? What are the use cases?