A local hybrid layered MCP Worker suite based on Ollama: **Vision Worker** (qwen2.5vl:7b) handles image understanding, while **Document Worker** (qwen3:4b) handles document engineering tasks, centrally orchestrated by a cloud-based main brain such as DeepSeek.
1 file for Codex and OpenCode: ollama-mcp-workers AGENTS.md — 182 tokens loaded in every session.
AGENTS.md A 182 tok These files are Crino-999/ollama-mcp-workers's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.