Phinq vs BDFL - Benevolent Delegator for LLMs

Phinq is an open-source runtime governance layer designed specifically for AI agents, built with the goal to stop AI agents before they make breaking or destructive errors.

As AI agents gain autonomy to execute tool calls, governance becomes critical. Phinq acts as a protective layer by intercepting every tool call made by an agent in real time. It analyzes and classifies each action based on risk level: safe, benign actions are automatically permitted to pass, while high-risk or irreversible actions are paused and held for human approval.

In addition to real-time risk classification and human-in-the-loop control, Phinq maintains complete accountability by recording every single decision into a tamper-evident, hash-chained audit log. This makes it a powerful developer tool for building reliable, safe, and auditable AI agent workflows.

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.