Show HN: Subagent-fleet – AI coding subagents across local Ollama machines (pypi.org)

The newly launched **subagent-fleet** project introduces a Python CLI tool designed for managing and running AI coding subagents across multiple local Ollama machines. This tool allows users to configure a local fleet of models—ranging from smaller, faster models for planning tasks to larger models for implementation and review. The innovative aspect of subagent-fleet lies in its ability to generate cohesive configurations that enable seamless interaction between different local models, enhancing the productivity of AI coding workflows. This development is significant for the AI/ML community as it facilitates more efficient use of local AI infrastructure, allowing developers to leverage multiple machines effectively. By offering features like model discovery, configuration generation, and node health monitoring while isolating unreachable nodes, subagent-fleet enhances workflow resilience and efficiency. The tool is compatible with existing frameworks like LiteLLM and Claude Code, thereby creating a flexible orchestration layer that simplifies the deployment and management of AI agents across diverse local environments.