Tameru

Good to know before installing

Subclasses Hermes's built-in ContextCompressor and overrides its private prune/demote methods (checks their shape at startup and falls back to stock compaction when they change). Unless you set compression.proactive_prune_tokens yourself, turns on proactive tool-result pruning with a trigger scaled to the model's context window, and after each prune shortens Hermes's re-prune runway. Adds a model-callable tameru_expand tool that returns pruned tool output from memory or from this session's archive (web, browser and MCP output stays wrapped as untrusted data); complex regex greps run in a short-lived local Python child process. No network calls; the render log is off by default.

From the plugin's catalog listing.