Delegates heavy, repetitive, and verifiable tasks like PDF extraction, code analysis, and log processing to a local LLM to reduce token consumption for frontier AI models, while keeping decision-making with the main AI.
Delegates tasks from an Anthropic-backed Claude Code session to Ollama-backed Claude Code sessions, allowing them to run side-by-side without sharing environment variables.
Enables delegating coding tasks to a pi agent as a steerable background worker, allowing mid-run redirection, follow-ups, and keeping the delegate's context isolated from your main conversation.
A delegation socket MCP server that enables a driver code agent to hand off subtasks to a cheap local worker (e.g., OpenCode) via a single MCP tool call and pick up results asynchronously without breaking flow.
