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
danbiocchi/hermes-vcc-engine
Hermes VCC Engine, also called the Instant Context Compactor, replaces the model call Hermes normally makes to summarize conversation history once a session approaches its context limit. Instead of asking the configured model to rewrite up to roughly 160,000 characters of history, which the README measures at a median of 8 minutes and up to 21 minutes on a local 27B model, it extracts facts from the middle of the conversation with fixed rules in about 0.055 seconds and zero model calls. The produced summary keeps the stated goal, a list of errors and their eventual fixes, every file read or modified, every command run with its exit code, and a tagged `[#N]` excerpt of each message, with every line linking back to the original archived message so the agent can reopen any excerpt in full through Hermes' `session_search`. Nothing is deleted; Hermes still archives originals in its own session database. The project reports a benchmark of 416 machine-graded recall questions asked in two wordings across 23 real compaction windows from 4 sessions, in which answers produced under the VCC-compacted context scored 91.0% correct, compared to 87.1% for the uncompacted full window, 76.2% for stock Hermes' LLM-written summary, and 74.5% for another similarly-named context-engine plugin in the Hermes catalog. On the next compaction, the previous VCC summary is merged rather than re-summarized, carrying the original goal and file/command lists forward. Installation is a one-line plugin install plus `hermes config set context.engine vcc`, reversible with the same command. It requires Hermes 0.21.7 or newer and has no runtime dependencies.
https://github.com/danbiocchi/hermes-vcc-engine
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.