zenith — MCP Server by Intelligent-Internet

by Intelligent-Internet · MCP Server · ★ 184

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

About zenith

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 () and the Intelligent Internet technical report (2026) behind it. Read the report (PDF) Abstract Long-running agents often fail not because they cannot make

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

Quick Facts

Stars184
Forks21
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score66.5058001661345/100
Open Issues6
Last Updated2026-07-02
Created2026-05-08
Platformsclaude-code, cli, codex, mcp, python
Est. Tokens~15k

Compatible Skills

These tools work well together with zenith for enhanced workflows:

  • qoreon — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)
  • agentic-grpo-longhorizon — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)
  • reins — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (59%)

zenith alternative? Top 6 similar tools

Looking for a zenith alternative? If you're comparing zenith with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • maestro by ReinaMacCredy · ⭐ 204

    Agent harness for codebases. Gives Claude Code, Codex, and CI a shared task system, verdict ledger, and state

  • sub-agents-mcp by shinpr · ⭐ 87

    Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.

  • SWE-AF by Agent-Field · ⭐ 891

    Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a

  • sandboxed.sh by Th0rgal · ⭐ 460

    Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX

  • OpenACP by Open-ACP · ⭐ 378

    Self-hosted bridge that lets you interact with AI coding agents (Claude Code, Codex, etc.) from messaging plat

  • hcom by aannoo · ⭐ 364

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is zenith?

zenith is 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.. It is categorized as a MCP Server with 184 GitHub stars.

What programming language is zenith written in?

zenith is primarily written in Python. It covers topics such as agent-client-protocol, agent-harness, ai-agents.

How do I install or use zenith?

You can find installation instructions and usage details in the zenith GitHub repository at github.com/Intelligent-Internet/zenith. The project has 184 stars and 21 forks, indicating an active community.

What license does zenith use?

zenith is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to zenith?

The top alternatives to zenith on Agent Skills Hub include maestro, sub-agents-mcp, SWE-AF. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse MCP Server tools