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
EfficientContext/ContextPilot
ContextPilot is a sophisticated context engine designed to enhance the performance of Large Language Model (LLM) inference, particularly in scenarios involving long contexts such as Retrieval Augmented Generation (RAG), memory-driven chatbots, and AI agent frameworks. It tackles the inefficiency of redundant computations when context blocks overlap or are reordered across requests, a common issue in dynamic LLM applications. ContextPilot operates by sitting between context assembly and inference, employing strategies like context indexing, reordering shared blocks into common prefixes, and deduplication of repeated content to maximize prefix reuse and minimize redundant KV recomputation. This process results in higher throughput, increased cache hits, and substantial token savings, as demonstrated by accelerated prefill times and reduced token consumption across various benchmarks. Crucially, it achieves these performance gains without compromising reasoning quality, even with extremely long contexts. ContextPilot provides drop-in solutions for integration with popular LLM ecosystems and agents, including OpenClaw and Nous Research Hermes Agent, and supports various inference backends like vLLM, SGLang, llama.cpp, and cloud APIs. Its architecture maintains a 'Context Index' and leverages 'cache-aware scheduling' to optimize prompt delivery, making it a valuable tool for developers seeking to deploy more efficient and scalable long-context LLM applications.
https://github.com/EfficientContext/ContextPilot
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.
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.