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
stepanov1975/hermes-local-knowledge
Hermes Local Knowledge is a reusable Hermes Agent plugin that builds a local search index over the artifacts an agent is likely to need: Markdown skills and their support documents, scripts under configured directories, runbooks and memory documents, cron job definitions, MCP server configuration, and generated tool-routing notes. It is explicitly an artifact router rather than chunk-based retrieval-augmented generation, a search result is a pointer to the one file the agent should open and read, not an assembled answer. It registers five native tools: knowledge_search to find candidate artifacts by intent with an optional type filter, knowledge_get to fetch one artifact (optionally with its graph neighbors), knowledge_neighbors to traverse related artifacts, knowledge_feedback to record whether a result was useful, missing, stale or wrong, and knowledge_usage_report to summarize search failures and zero-result queries for tuning. Lifecycle hooks (pre_llm_call, on_session_end, on_session_finalize) inject a one-line system-prompt hint on new sessions nudging the agent to search before it falls back to broad file search, and the plugin learns implicit routing feedback by watching when the same artifact is actually opened after a matching search within the same session, task and turn, tightening its ranking over time without requiring the user to rate every result. An optional, on-by-default background feature uses the active model to auto-generate short routing notes for content the index has not yet described well, bounded to a small number of candidates and one batch call per session so it adds, rather than dominates, token use; it can be disabled for users who do not want the extra model calls. The plugin installs as a standard directory plugin from Git or SSH and targets Hermes users running substantial local skill, script and runbook collections who want faster, more precise routing to the right file than general-purpose file search provides.
https://github.com/stepanov1975/hermes-local-knowledge
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.
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.