Enables Claude Code to delegate coding implementation and testing to a local pi agent via MCP tools, including dispatching task books, monitoring status, steering or aborting runs mid-execution, and retrieving results and transcripts.
Enables launching and supervising local Codex and Claude Code agent sessions and one-shot tasks, exposing run, list, stop, and output operations over MCP with session-scoped permissions and sandbox controls.
Delegates bounded coding tasks from MCP clients to the Pi Coding Agent over stdio. Supports review, verification, implementation, and batch operations with long-running task polling.
Enables external clients to spawn, control, observe, and terminate isolated AI coding agent sessions over MCP via stdio or Streamable HTTP, with scoped chip datasheet knowledge-base retrieval.