Which AI agent harnesses lead right now?

On one day's OpenRouter token count, Hermes Agent (1.73 trillion) and Claude Code (1.55 trillion) lead, then pi, Kilo Code and Codex. By GitHub stars, Hermes Agent (261k) and OpenCode (225k) lead. OpenCode and Antigravity do not appear in the token list at all, so neither ranking covers all seven. Read 2026-11-06.

By Mackenzie Bowes · mackenzie@mackenziebowes.com · @_mackenziebowes on X

Contents

Short answer, from the sources below: there is no single ranking of agent harnesses, and the two public measures found here disagree. On one day of tokens sent through OpenRouter, Hermes Agent and Claude Code lead by a wide margin.[1] By GitHub stars, Hermes Agent and OpenCode lead, then Claude Code, Codex and pi.[2][3][4][5][6] Cursor and Antigravity have no repository among the pages read, so stars say nothing about them. This is a first page in a series: how these harnesses handle memory, tool calls, hooks and heartbeats comes on later pages.

A harness here means the program around a model that reads files, runs commands, calls tools and loops until a task is done, as distinct from the model itself. The seven named on this page are the ones Mackenzie listed; the OpenRouter list shows others that are not covered.

Measure one is tokens on OpenRouter

OpenRouter is a service that routes requests to many models, and it publishes a ranking of the apps that send traffic through it. The "CLI Agents" ranking, on the Tokens tab for the period "Today", read at about 10:30 Mountain time on 2026-11-06, was:[1]

RankHarnessTokens that day
1#Hermes Agent1.73 trillion
2#Claude Code1.55 trillion
3#pi684 billion
4#omp673 billion
5#Kilo Code659 billion
6#OpenClaw584 billion
7#Codex450 billion
13#Cursor57.9 billion

The wider "Coding" ranking, read the same morning, had the same first seven places.[7] Cursor sat at 14 there. Neither list showed OpenCode in the ranks read (1 to 39 and 1 to 17), and neither showed Antigravity.

What this measures: only tokens that went through OpenRouter, on one day. A tool whose users send their requests straight to a model maker would be undercounted, and the page does not say how it identifies an app. It is a snapshot, not a trend.

Measure two is GitHub stars

Stars were read from each project's repository page on 2026-11-06. They show how many people marked a project, not how many use it.

Two OpenCode projects share the name. The older repository, opencode-ai/opencode, is archived with the note that the project continued as Crush, by the original author and the Charm team, and it has 13.9k stars.[8] Crush is at rank 22 in the OpenRouter CLI list.[1] The OpenCode site and the 225k-star repository belong to a different project.[9]

What each one says it is

These are each project's own descriptions, so they are claims, not tests.

What the two measures rule out

These are consequences of the numbers, not findings from a source.

Terms

Not yet proven

If you pick a harness for real work and the ranking here led you wrong, I would like to hear it: mackenzie@mackenziebowes.com.

Sources

  1. OpenRouter, "CLI Agents Rankings", Tokens tab, period Today. Read in Rotunda 2026-11-06. The page text had no figures, so they were typed from a screenshot of the page. openrouter.ai/apps/category/coding/cli-agent
  2. GitHub, NousResearch/hermes-agent. Read in Rotunda 2026-11-06. github.com/nousresearch/hermes-agent
  3. GitHub, anomalyco/opencode. Read in Rotunda 2026-11-06. github.com/anomalyco/opencode
  4. GitHub, anthropics/claude-code. Read in Rotunda 2026-11-06. github.com/anthropics/claude-code
  5. GitHub, openai/codex. Read in Rotunda 2026-11-06. github.com/openai/codex
  6. GitHub, earendil-works/pi. Read in Rotunda 2026-11-06. github.com/earendil-works/pi
  7. OpenRouter, "Coding" apps ranking, Tokens tab, period Today. Read in Rotunda 2026-11-06; first screen only, typed from a screenshot. openrouter.ai/apps/category/coding
  8. GitHub, opencode-ai/opencode (archived). Read in Rotunda 2026-11-06. github.com/opencode-ai/opencode
  9. OpenCode, home page. Read in Rotunda 2026-11-06. opencode.ai/
  10. Claude Code Docs, Overview. Read in Rotunda 2026-11-06. code.claude.com/docs/en/overview
  11. Cursor Docs, Agent overview. Read in Rotunda 2026-11-06. cursor.com/docs/agent/overview
  12. Google Antigravity, "Introducing Google Antigravity". Read in Rotunda 2026-11-06. antigravity.google/blog/introducing-google-antigravity/
  13. Mario Zechner, "What I learned building an opinionated and minimal coding agent", 2025-11-30. Read in Rotunda 2026-11-06; its contents list was read, not the full post. mariozechner.at/posts/2025-11-30-pi-coding-agent/

Terms on this page

  • Agent memory: Information an AI agent writes down in one session and reads back in a later one.
  • Hook: A command that an AI coding agent runs automatically at a set point in its work.
  • Model Context Protocol: An open standard for connecting AI applications to outside tools and data.
  • Tool call: A request from an AI model to run one action, such as a search or a file write, which the surrounding program carries out.