Skip to main content
ClaudeWave
EN, English
RyanAlberts / Subagents · Official registry

best-of-Agent-Harnesses

🏆 Ranked list of 167 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.

  • 1.3k stars
  • 90 forks
  • 41 open issues
  • Language: Python
  • License: CC-BY-SA-4.0
  • updated
Install in ClaudeView on GitHub

Install

Terminal
git clone https://github.com/RyanAlberts/best-of-Agent-Harnesses && cp best-of-Agent-Harnesses/*.md ~/.claude/agents/
  1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
  2. Start a new Claude Code session to load the agents.
  3. Delegate work to them with the Task/Agent tool or by name.
Installable items

3 items in this repository

harness-radarSubagent

Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — from the best-of-Agent-Harnesses dataset, which rescores itself every week. Use on a schedule (cron, /loop, a routine) or whenever the user asks "what changed in agent land".

Install
harness-scoutSubagent

Picks the right AI agent harness for a described task or project. Use when the user asks "what harness/framework/agent tool should I use", compares agent frameworks, or starts an agent project without a stack decision. Grounded in the live best-of-Agent-Harnesses dataset, never in training-data memory.

Install
stack-auditorSubagent

Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage.

Install
README

Subagents overview

README preview not available. Visit the repo on GitHub for full documentation.
Use cases
AI / ML Education
Topics
agent-frameworkagent-harnessagentic-aiagentsai-agentai-agent-frameworkai-agentsai-toolsawesome-listbest-of-listclaude-codecoding-agentsharnessharness-engineeringllmllm-agentsllm-frameworkllm-toolsmcpmodel-context-protocol
Frequently asked

What people ask about best-of-Agent-Harnesses

What is RyanAlberts/best-of-Agent-Harnesses?

RyanAlberts/best-of-Agent-Harnesses is subagents for the Claude AI ecosystem. 🏆 Ranked list of 167 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly. It has 1.3k GitHub stars and its last recorded update is dated 2026-10-18.

How do I install best-of-Agent-Harnesses?

You can install best-of-Agent-Harnesses by cloning the repository (https://github.com/RyanAlberts/best-of-Agent-Harnesses) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is RyanAlberts/best-of-Agent-Harnesses safe to use?

Our security agent has analyzed RyanAlberts/best-of-Agent-Harnesses and assigned a Trust Score of 87/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.

Who maintains RyanAlberts/best-of-Agent-Harnesses?

RyanAlberts/best-of-Agent-Harnesses is maintained by RyanAlberts. The last recorded GitHub activity is dated 2026-10-18, with 41 open issues.

Are there alternatives to best-of-Agent-Harnesses?

Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.

Project homepage
https://ryanalberts.github.io/best-of-Agent-Harnesses/