token-rate.yaml 1.4 KB

123456789101112131415161718192021222324252627282930
  1. name: token-rate
  2. repo: https://github.com/Lazzdaycod/hermes-lang-it
  3. sha: d678baf37018398bf9c38afbb418d43e11b82a8e
  4. subdir: plugins/token-rate
  5. title: Token Rate Monitor
  6. description: >-
  7. Live output/input tokens-per-second chip in the Hermes Desktop status bar for a
  8. local llama.cpp server. Hermes itself reads the server's log
  9. ($HERMES_HOME/logs/llama-server.log, last 200 lines: `tg = X t/s` for output and
  10. `prompt eval time ... X tokens per second` for input) and serves it at
  11. /api/plugins/token-rate/; the chip polls that route once a second. The counter
  12. starts off — click the chip, or run the palette entry "Token Rate: start/stop
  13. the tok/s counter" (Ctrl/Cmd+K), to start it; the on/off flag is a file
  14. ($HERMES_HOME/cache/token-rate-state.json). It also registers the
  15. get_token_rate agent tool, so the model can read its own speed. Disclosure —
  16. it reads one local file (the llama.cpp log) and nothing else: no network calls,
  17. no external process, no extra port, no API key, no credentials, no telemetry.
  18. UI is English by default, Italian when the app locale is Italian.
  19. maintainer: Lazzdaycod
  20. tier: community
  21. category: desktop
  22. requires_hermes: ">=0.21.6"
  23. docs_url: https://github.com/Lazzdaycod/hermes-lang-it/tree/main/plugins/token-rate
  24. version: "2.0.0"
  25. platforms: []
  26. capabilities:
  27. provides_tools: [get_token_rate]
  28. provides_hooks: []
  29. provides_middleware: []
  30. requires_env: []