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
beniedev/moonbite
Moonbite is an experimental continuity layer that runs alongside Hermes Agent rather than replacing it: Hermes keeps ownership of models, tools, credentials, scheduling and delivery, while Moonbite adds memory, present-state awareness, and judgment about whether to act. Its components are a Memory/Diary that remembers across sessions with searchable, evidence-preserving references, a Panel/Daily RAM holding bounded short-lived working state with daily rollover, a Heartbeat that is a decision pipeline (not a timer) for whether something deserves attention or escalation, an Autonomy module that performs at most one eligible host-triggered activity per tick and records failures rather than retrying with a different action, and a Runtime Core keeping events and decisions in append-only records. Every visible external action requires a matching execution receipt from the host before it is considered accepted, and the project explicitly does not include its own scheduler, credential store, network browser, or messaging channel. The Hermes adapter registers ten tools and seven lifecycle hooks (pre_gateway_dispatch, on_session_start, pre_llm_call, post_llm_call, on_session_end, on_session_finalize, subagent_stop). By default only the runtime_core module is enabled; heartbeat, autonomy, panel and memory are off, and installation alone triggers no background task, model call, network request or message. Recommended installation pins an immutable commit SHA through hermes plugins install rather than tracking a floating branch, followed by a doctor command that performs no writes or network probes. The project is a public preview supporting only Hermes as a host, on Linux, WSL2 and macOS, with no stable API guarantee yet. MIT licensed.
https://github.com/beniedev/moonbite
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.
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.