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
ranxianglei/billion-context
billion-context is a universal context-compression proxy that sits between any AI coding agent and its model API, rewriting Anthropic- and OpenAI-shaped request/response streams so long sessions can run for days without hitting the context window; it is built on the author's acp-kernel compression library and backs a production-scale study reporting 4.5 months, three hosts, and over 18 billion cumulative input tokens with zero window violations on 204,800-token models. Rather than a hard truncation limit, the proxy lets the model itself decide when and what conversation history to compress into layered, high-fidelity summaries that are incremental, reversible, and written to preserve the prompt-cache prefix. Its repository root hermes-plugin/ directory packages this as a dedicated native Hermes Agent plugin (installed with bili plugin install hermes) rather than a generic adapter: plugin.yaml declares the pre_api_request hook and the compress, decompress, and acp_status tools, and __init__.py spawns billion-context's own bili proxy on an ephemeral port (or reuses a healthy one), routes model traffic through it via HTTPS_PROXY and a Hermes CA bundle using the same CONNECT-plus-certificate-MITM wire path as the project's standalone launcher, registers the proxy's tools as native Hermes tools, and stamps plugin-mode headers on requests once those tools are ready. The plugin is explicitly written fail-open: any internal error falls back to Hermes talking to the upstream model directly rather than raising, and it depends only on the Python standard library plus a best-effort PyYAML import that Hermes itself already requires. The wider project also publishes a research paper on the compression method and community channels for its billion-context, billion-context-pi, and opencode-acp sibling tools.
https://github.com/ranxianglei/billion-context
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...
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.