mpai vs BDFL - Benevolent Delegator for LLMs

mpai is an open-source terminal developer tool designed to bring real-time multiplayer collaboration to existing Codex and Claude Code AI sessions. Created by Reagan Stock, the tool enables software engineers to collaborate directly inside command-line AI workflows without losing session history or context.

Using mpai, team members can join an explicitly shared native session from another Mac and immediately access the full context of the active conversation. Prompts sent by collaborators arrive with their name attached to distinguish inputs. To ensure security and control, mpai relies on Tailscale to keep network traffic private, while the host Mac remains in full control of the session.

BDFL (Benevolent Delegator for LLMs) is an open-source terminal supervisor designed to orchestrate complex coding sessions using AI agents like Codex, Claude Code, and Ollama. Instead of relying on a single AI window, BDFL separates the workflow into specialized roles. Users interact with a 'planning agent' to create versioned, deliberate plans. Once the human user approves the plan—or specific sections of it—BDFL automatically delegates the tasks to isolated 'worker agents' that execute the code in parallel. Beyond just task delegation, the platform handles the heavy lifting of scheduling, running checks, verifying code, and managing integration. Every worker operates in an isolated environment, ensuring that code changes are properly sandboxed and reviewed before being merged. Because it operates entirely locally without any telemetry or centralized tracking, BDFL offers developers a secure, deterministic, and highly observable way to scale their AI-assisted software development.