llmslim.yaml 1.2 KB

1234567891011121314151617
  1. name: llmslim
  2. title: LLMSlim
  3. repo: https://github.com/Thanatos9404/llmslim
  4. sha: 34c6f80a28fce47309f6a18bffe0df7bf40d296f
  5. subdir: plugins/hermes
  6. description: "Context engine that compresses older tool output and turns locally with LLMSlim instead of asking a model for a summary: no LLM call, deterministic output, and the start of the prompt is sent unchanged, so prompt caching keeps working. Select it with context.engine: llmslim. Disclosure: installs llmslim==0.12.0 from PyPI (with numpy, scikit-learn and jsonschema); registers no tools, hooks or middleware; makes no network calls, runs no shell commands, needs no credentials, writes no files and sends no telemetry; reads its settings from config.yaml through Hermes's config loader. Token counts use a character estimate unless tiktoken is already installed in Hermes's environment, in which case tiktoken may download its encoding file once."
  7. maintainer: Thanatos9404
  8. tier: community
  9. category: general
  10. requires_hermes: ">=0.21.7"
  11. docs_url: https://github.com/Thanatos9404/llmslim/blob/main/docs/integrations/HERMES.md
  12. version: "0.12.0"
  13. capabilities:
  14. provides_tools: []
  15. provides_hooks: []
  16. provides_middleware: []
  17. requires_env: []