Is the zenith MCP server actively maintained?

The zenith MCP server was last committed 2mo ago and has 9 contributors. Issue health: 32% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

zenith MCP Server

Name: Intelligent-Internet/zenith
Rating: 3.5 (1 reviews)
Author: Intelligent-Internet

Intelligent-Internet/zenith

Score: 62.5 Rank #5628 Agent Framework

[![AgentRank](https://agentrank-ai.com/api/v1/badge/Intelligent-Internet--zenith)](https://agentrank-ai.com/tool/Intelligent-Internet--zenith/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of Intelligent-Internet/zenith? Claim this listing →

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.

Add AgentRank to Claude Code Discover and compare tools like Intelligent-Internet/zenith — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

Intelligent-Internet/zenith is a Python tool licensed under Apache-2.0. 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. Topics: agent-client-protocol, agent-harness, ai-agents, claude-code, codex, llm, long-horizon-tasks, mcp, model-context-protocol, multi-agent, orchestration.

Ranked #5628 out of 24846 indexed tools.

Ecosystem

Python Apache-2.0

agent-client-protocolagent-harnessai-agentsclaude-codecodexllmlong-horizon-tasksmcpmodel-context-protocolmulti-agentorchestration

Score Breakdown

Stars 15% 346

346 stars → growing community

Freshness 25% 2mo ago

Last commit 2mo ago → moderate activity

Issue Health 25% 32%

7/22 issues closed → many open issues

Contributors 10% 9

9 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 51

Description Detailed

License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Freshness high impact

Last commit was 66 days ago — a recent commit would boost your freshness score

Issue Health high impact

You have 15 open vs 7 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/Intelligent-Internet--zenith)](https://agentrank-ai.com/tool/Intelligent-Internet--zenith/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/Intelligent-Internet--zenith/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/Intelligent-Internet--zenith" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="Intelligent-Internet/zenith"></script>

Details

Stars: 346
Forks: 51
Open Issues: 15
Closed Issues: 7
Contributors: 9
Dependents: —
Language: Python
License: Apache-2.0
Last Commit: 2mo ago

Matched Queries

topic:mcptopic:model-context-protocol

From the README

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

<p>
  <a href="https://github.com/Intelligent-Internet/zenith/actions/workflows/ci.yml"></a>
  <a href="LICENSE"></a>
  
  <a href="technical_report/Technical_Report.pdf"></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

Read full README on GitHub →