LLMSlim
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.
Good to know before installing
Installs llmslim==0.11.2 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.
From the plugin's catalog listing.
How to install
- Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install llmslim - Said no? Turn it on later:
hermes plugins enable llmslim - Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide (opens in a new tab).
- Category
- Cost, speed & monitoring
- Maintained by
- Thanatos9404 (Community)
- Needs
- No API keys declared
- Needs Hermes
- 0.21.7 or newer
- Version
- 0.11.2
- In the catalog
- 2026-10-20, updated 2026-10-27
- GitHub stars
- 22
Full setup & settings ↗Source code ↗
More in cost, speed & monitoring
All cost, speed & monitoring plugins
New Hermes Agent updates every day on X. Follow @HermesWatcher