stephenschoettler/hermes-lcm
hermes-lcm is a lossless context management plugin for Hermes Agent, providing a DAG-based context engine that ensures no messages are lost through persistent storage and intelligent summarization.
Awesome Hermes Plugins › Context Engines
byenzyme/enzyme-skill
Enzyme packages the enzyme concept-graph engine as a Hermes Agent plugin and an OpenClaw skill, giving an agent structural memory over Obsidian vaults, Markdown knowledge bases and other accumulated document corpora. Its argument is that retrieval-augmented generation and conversational memory tools both pay tokens and latency at query time, so enzyme instead runs a compile step over the workspace. It reads tags, links, folders and timestamps, generates thematic questions it calls catalysts across the full timeline, and precomputes relationships, so that a query becomes a local database lookup of roughly eight milliseconds with no LLM or API call. The plugin registers three lifecycle hooks and five tools. on_session_start bootstraps the binary when it is missing and runs enzyme refresh; pre_llm_call fires on the first user message, runs enzyme petri with that message and injects relevant entities and catalysts as ephemeral context; on_session_end reindexes notes written during the session. The tools are enzyme_petri for a vault overview of trending entities and activity, enzyme_catalyze for semantic search returning excerpts, file paths and the catalysts that bridged the match, enzyme_refresh for incremental reindexing, enzyme_status for document and entity counts with embedding coverage, and enzyme_init for first-time vault setup. Tools are gated by a check function and stay hidden from the model until the enzyme binary is on PATH. Installation is hermes plugins install useenzyme/enzyme-skill, with a self-installing binary bootstrap of about thirty-eight megabytes on the first run. Catalyst generation uses an LLM: the first vault initialisation can use the hosted bootstrap of the project, while refresh and further vaults use an account, or a user-supplied OpenAI-compatible provider selected with the --use-env-llm flag. The core CLI lives in a separate repository.
https://github.com/byenzyme/enzyme-skill
Also in Context Engines
claudioemmanuel/squeez
squeez is an end-to-end token optimizer that provides hook-based token compression for Hermes Agent and several other AI CLI hosts, increasing context window efficiency.
EfficientContext/ContextPilot
ContextPilot is a context engine that accelerates long-context LLM inference by optimizing context reuse, offering significant speedups and token savings for RAG, memory chat, and agentic AI worklo...
beniedev/moonbite
Experimental Hermes Agent plugin adding cross-session memory, short-lived working state, and bounded, verified autonomous action on top of the host agent.
eas4ai/hermes-context-manager
Silent-first context optimization plugin for the Hermes Agent gateway that compresses tool outputs, deduplicates repeated work and summarizes completed phases without the main model noticing.
kenyonxu/hermes-persona
hermes-persona is a configurable Hermes Agent plugin that dynamically injects persona context into LLM calls using various hooks and rules.
Sahil-SS9/hermes-memlock
Hermes plugin that detects context compaction, audits which pinned standing instructions survived outside the summary region, and rehydrates the lost ones as a reminder block.
PlayForm/Aphrodite-Hermes
Compresses Hermes tool output before it reaches the model into compact retrievable previews, via a thin Python loader calling a Rust classifier and store, cutting per-call token cost.