{"repo":"Intelligent-Internet/zenith","free":true,"listed":false,"github":"https://github.com/Intelligent-Internet/zenith","clone":"git clone https://github.com/Intelligent-Internet/zenith.git","description":"Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.","language":"Python","stars":279,"topics":["agent-client-protocol","agent-harness","ai-agents","claude-code","codex","llm","long-horizon-tasks","mcp","model-context-protocol","multi-agent"],"license":"Apache-2.0","category":"ai-agents","readme_excerpt":"Zenith: A Continuous-Improvement Harness for Long-Running Tasks 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/ ) and the Intelligent Internet technical report (2026) behind it. Read the 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. RALPH is the strongest simple baseline because it forces each new session to reopen the gap between the current project state and the original requirement. But RALPH is expensive and has no principled stopping rule. Our Zenith method keeps the useful parts of repeated review while making the loop adaptive: the orchestrator dynamically allocates workers, testers, reusable skills, replanning, and stopping decisions. In this study, Zenith achieved the best mean rank while using less than half of RALPH's per-task cost. Qu","default_branch":null,"files":null,"tree":[],"storefront":"/r/Intelligent-Internet","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Intelligent-Internet/zenith/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}