| 1234567891011121314151617 |
- name: model-drift-watch
- repo: https://github.com/TakeshiTGAL/hermes-plugin-model-drift
- sha: 0102786ba4812e8581f3f6234a453eb26137fa52
- description: "Scheduled check that the model you use in Hermes has not quietly got worse: 34 fixed, exactly graded questions (reasoning, instruction following, Japanese, plus your own) run through Hermes cron, each run tested against the same model's own baseline with an exact per-question test and a same-day confirmation run, and a message only for a confirmed drop, a changed served model or a failed measurement. Not yet tried against a real LLM API (checked with a local mock model and real Hermes cron). Disclosure — each check calls your own model through ctx.llm on your bill, capped per check by the plugin (default 120,000 tokens / $0.50, no daily cap; the agent can start checks itself via the model_drift tool, and the scheduled agent turn is extra); price lookup goes through Hermes's pricing code (may fetch OpenRouter/models.dev prices); 10 optional code questions, off by default, run model-written Python in a limited child process (not a hostile-code sandbox) including in unattended cron runs when enabled; `schedule` creates one Hermes cron job that survives plugin removal (run `unschedule` first); writes run history to plugin-data/model-drift-watch; no telemetry."
- maintainer: TakeshiTGAL
- tier: community
- category: automation
- docs_url: https://github.com/TakeshiTGAL/hermes-plugin-model-drift#readme
- version: "0.1.0"
- requires_hermes: ">=0.21.5"
- platforms: []
- capabilities:
- provides_tools:
- - model_drift
- provides_hooks: []
- provides_middleware: []
- requires_env: []
|