ranxianglei/billion-context
Native Hermes hook plugin registering compress/decompress/acp_status tools that route model traffic through billion-context's self-spawned context-compression proxy.
Awesome Hermes Plugins › Context Engines
Elevatormusic/hermes-warm-compaction
warm_compaction is a context-engine plugin for Hermes Agent that changes how context compaction works without requiring a patched host. At each compaction event, the main model writes its handoff summary over the already-cached prefix of its last request, so the inference server only has to read the small number of new rows appended since that request rather than reprocessing the full conversation. This keeps compaction fast even as sessions grow long. The plugin is implemented entirely through documented Hermes plugin APIs: it does not patch the host, subclass the built-in compressor, or wrap Hermes internals at runtime, so it works on an unpatched Hermes Agent install and can be enabled or disabled independently. The author publishes a self-benchmark comparing warm_compaction against both the Hermes built-in compactor and the third-party hermes-lcm plugin. Measured median compaction time was 16.8 seconds for warm_compaction versus 43.5 seconds for hermes-lcm and 78.5 seconds for the built-in compactor; including the next reply after compaction, the totals were 27.9s, 66.1s and 97.1s respectively. On a fact-retention benchmark, warm_compaction kept 59 of 60 compacted facts versus 43/60 for hermes-lcm and 50/60 for the built-in compactor, and recovered facts placed in the middle of a long message far more reliably. The project is written in Python 3.10+, has no runtime dependencies, ships CI tests and a lint workflow, and is released under the Apache-2.0 license. It targets users who run long Hermes Agent sessions and are hitting slow or lossy compactions with the default compactor.
https://github.com/Elevatormusic/hermes-warm-compaction
Also in Context Engines
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.
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...
electricsheephq/lcm-x
Lossless Context Memory eXtension (hermes-lcm-x): a SQLite-backed, DAG-based context engine for Hermes Agent that persists raw messages and compacts them into recoverable summary hierarchies instead of discarding detail.
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.
byenzyme/enzyme-skill
A Hermes plugin that compiles a Markdown vault into a local concept graph and injects trending entities and semantic search results into the session through three lifecycle hooks and five tools.
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.