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
stephenschoettler/hermes-lcm
The hermes-lcm project implements a Lossless Context Management plugin for Nous Research Hermes Agent, offering an advanced context engine that replaces the default one-shot active-context compression with a SQLite-backed, DAG-based system. Unlike traditional compression that can lead to information loss in the active context, hermes-lcm persists all messages, compacts older context into depth-aware summary nodes, and condenses these summaries into a hierarchical Directed Acyclic Graph (DAG). This approach ensures that while the live prompt remains bounded, the agent retains the ability to recover exact details after compaction. The plugin leverages a SQLite message store for raw messages, a summary DAG for historical context, and provides bounded recovery mechanisms for detailed retrieval without flooding the main prompt. It includes a comprehensive suite of agent tools such as `lcm_grep`, `lcm_load_session`, `lcm_describe`, `lcm_expand`, `lcm_expand_query`, `lcm_status`, `lcm_inspect`, and `lcm_doctor` for search, inspection, and expansion of compacted material. Additionally, hermes-lcm offers source-aware retrieval, session controls, large payload management, and sensitive pattern redaction for enhanced data handling and security. It directly addresses the challenge of maintaining conversational continuity and detailed recall in long-running agent interactions, distinguishing itself from standard compression by integrating recall directly into the active context engine.
https://github.com/stephenschoettler/hermes-lcm
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...
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.
Elevatormusic/hermes-warm-compaction
Context-engine plugin for Hermes Agent that speeds up compaction by writing the handoff summary against the cached prompt prefix instead of the whole transcript.
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.