Intelligent-Internet/zenith

README preview

# Zenith: A Continuous-Improvement Harness for Long-Running Tasks

<img width="1500" height="600" alt="From RALPH to Zenith — Intelligent Internet technical report" src="https://github.com/user-attachments/assets/8c3c76e7-4a54-4c6e-95b7-25db573a0881" />

<p>
  <a href="https://github.com/Intelligent-Internet/zenith/actions/workflows/ci.yml"><img src="https://github.com/Intelligent-Internet/zenith/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
  <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-blue.svg" alt="License: Apache-2.0"></a>
  <img src="https://img.shields.io/badge/python-3.11%2B-blue.svg" alt="Python 3.11+">
  <a href="technical_report/Technical_Report.pdf"><img src="https://img.shields.io/badge/technical%20report-PDF-b31b1b.svg" alt="Technical Report"></a>
</p>

Zenith is an agent harness for work that may run for days or weeks, where the dominant failure mode is *premature completion* rather than inability to make progress. It runs a coding agent (Claude Code, Codex, or Hermes) as a multi-agent orchestrator over MCP/ACP: one orchestrator session reads task state each turn and decides whether to spawn workers and testers, register reusable skills, replan, or stop.

This repository contains the Zenith harness ([`zenith/`](zenith/)) and the Intelligent Internet technical report (2026) behind it.

> **[Read the report (PDF)](technical_report/Technical_Report.pdf)**

## Abstract

Long-running agents often fail not because they cannot make progress, but because they stop before the task is truly complete. We tested five harness designs across eight long-horizon tasks to isolate the control mechanisms that matter: repeated gap-finding, revisable planning, independent verification, adaptive orchestration, and stopping discipline.

View full repository on GitHub →