Skip to content

The agent that grows with you

1.4 KB
Raw Blame
name: token-rate
repo: https://github.com/Lazzdaycod/hermes-lang-it
sha: d678baf37018398bf9c38afbb418d43e11b82a8e
subdir: plugins/token-rate
title: Token Rate Monitor
description: >-
  Live output/input tokens-per-second chip in the Hermes Desktop status bar for a
  local llama.cpp server. Hermes itself reads the server's log
  ($HERMES_HOME/logs/llama-server.log, last 200 lines: `tg = X t/s` for output and
  `prompt eval time ... X tokens per second` for input) and serves it at
  /api/plugins/token-rate/; the chip polls that route once a second. The counter
  starts off — click the chip, or run the palette entry "Token Rate: start/stop
  the tok/s counter" (Ctrl/Cmd+K), to start it; the on/off flag is a file
  ($HERMES_HOME/cache/token-rate-state.json). It also registers the
  get_token_rate agent tool, so the model can read its own speed. Disclosure —
  it reads one local file (the llama.cpp log) and nothing else: no network calls,
  no external process, no extra port, no API key, no credentials, no telemetry.
  UI is English by default, Italian when the app locale is Italian.
maintainer: Lazzdaycod
tier: community
category: desktop
requires_hermes: ">=0.21.6"
docs_url: https://github.com/Lazzdaycod/hermes-lang-it/tree/main/plugins/token-rate
version: "2.0.0"
platforms: []
capabilities:
  provides_tools: [get_token_rate]
  provides_hooks: []
  provides_middleware: []
  requires_env: []