mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-11-06 05:17:15 +00:00
31 lines
1.4 KiB
YAML
31 lines
1.4 KiB
YAML
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: []
|