← Back to Portfolio

tiny-agent-harness

2026.03

Project Overview

A toy project that reconstructs the supervisor-led multi-agent harness pattern seen in tools like OpenAI Codex CLI and Anthropic Claude Code. It keeps planning, execution, review, tool calls, and event channels explicit so the whole architecture stays readable and easy to experiment with.

Problem Definition & Goals

Key Features & Contributions

Results & Learnings

Technologies

Python Pydantic OpenAI API OpenRouter PyYAML pytest

Links