No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Intelligent-Internet · MCP Server · ★ 273
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is zenith safe to install? View the security audit →
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
| Stars | 273 |
| Forks | 38 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 66.5058001661345/100 |
| Open Issues | 20 |
| Last Updated | 2026-08-07 |
| Created | 2026-05-08 |
| Platforms | claude-code, cli, codex, mcp, python |
| Est. Tokens | ~15k |
These tools work well together with zenith for enhanced workflows:
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.
The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent j
Agent harness for codebases. Gives Claude Code, Codex, and CI a shared task system, verdict ledger, and state
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and works
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular,
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a
Explore other popular mcp server tools:
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 273 GitHub stars.
zenith is primarily written in Python. It covers topics such as agent-client-protocol, agent-harness, ai-agents.
You can find installation instructions and usage details in the zenith GitHub repository at github.com/Intelligent-Internet/zenith. The project has 273 stars and 38 forks, indicating an active community.
zenith is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to zenith on Agent Skills Hub include oh-my-agent, maestro, sub-agents-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.