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.
Awesome Hermes Plugins › Context Engines
PlayForm/Aphrodite-Hermes
Aphrodite-Hermes is a context-compression plugin for Hermes Agent: it intercepts tool output before it reaches the model and replaces bulky text with a compact structured preview, retrieving the full content only when the agent actually asks for it via a marker token - the README claims roughly 15 tokens of metadata in place of 500 tokens of raw output. The Python side is a thin loader (five lifecycle hooks, thirteen tools) that talks over ctypes FFI to a Rust dynamic library, which does all classification (a 26-type classifier), compression and storage (a local SQLite store); Python only serves as a fallback if the dylib is unavailable, and a hot-reload path picks up a rebuilt dylib automatically. Because the compression proxy is itself an OpenAI-compatible API relay, it needs its own upstream LLM credentials separate from whatever provider Hermes is already configured with - there is no keyless or compression-only mode, and the proxy refuses to start without an API key. Installation symlinks the repository into the Hermes plugins directory, enables the plugin, and on first launch downloads a prebuilt binary (no Rust toolchain needed) that runs two local proxy processes for caching and tokenization. Tuning lives in a TOML config (engine trigger threshold as a percentage of context fill, how many leading and trailing messages to always protect, per-tool byte thresholds, a code-length multiplier) with environment-variable overrides, and behavior can be steered further with swappable text directives loaded from a configurable directory. Exposed tools cover retrieving and searching compressed content, viewing proxy health and the full catalog, listing tracked file references and conversation diffs, prefetching and reclassifying content, and running a built-in smoke test suite. It targets Hermes users running long sessions or large tool outputs who want to extend effective context length without switching models. Licensed CC0.
https://github.com/PlayForm/Aphrodite-Hermes
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...
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.
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.
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.
kenyonxu/hermes-persona
hermes-persona is a configurable Hermes Agent plugin that dynamically injects persona context into LLM calls using various hooks and rules.
Sahil-SS9/hermes-memlock
Hermes plugin that detects context compaction, audits which pinned standing instructions survived outside the summary region, and rehydrates the lost ones as a reminder block.