Caveman vs BDFL - Benevolent Delegator for LLMs

Caveman is an open-source developer tool designed around a simple yet powerful premise: "why use many token when few do trick." Built by maker Julius Brussee, Caveman allows developers to wrap AI coding assistants and LLM workflows—such as Claude Code, Codex, and Hermes—with a single command.

At its core, Caveman operates as a local proxy that intelligently compresses logs, tool outputs, and source code files before sending them to LLM provider endpoints. In a pinned 54-run benchmark, Caveman reduced input tokens by 33.2% while achieving 18/18 correctness checks, ensuring token savings do not compromise code or task accuracy.

In addition to compressing standard logs and file outputs, Caveman can execute existing agent skills with approximately 70% fewer tokens by rendering and loading text as images. Backed by a thriving open-source ecosystem with over 97,000 GitHub stars, Caveman provides a practical, efficient solution for optimizing developer workflows and reducing API usage costs.

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.