Files
hermes-agent/plugin-catalog/hermes-lcm-x.yaml

48 lines
2.2 KiB
YAML

name: hermes-lcm-x
title: LCM-X
repo: https://github.com/electricsheephq/lcm-x
sha: 2f3a96623d351649a0714eb42d98ff5b945337f2
description: 'Lossless context memory engine: instead of lossy compaction, LCM-X keeps every turn in a local SQLite store (lcm.db)
and builds a recoverable DAG of summaries over it, with 15 lcm_* tools to search, recall and expand earlier context. Select it
with context.engine: lcm-x. Upgrading from hermes-lcm (breaking in v0.24.0): stop Hermes, then in plugins.enabled replace
hermes-lcm with hermes-lcm-x and run exactly one LCM copy (the install script prints the steps; the old engine name lcm
still resolves with a deprecation warning); lcm.db and the lcm: config block are unchanged.
Summaries use the model Hermes is configured with. Disclosure — optional semantic recall (embeddings_enabled, off by
default) sends message text to the embedding provider you configure (Voyage via VOYAGE_API_KEY, or an OpenAI-compatible
endpoint, or a local Ollama); for known cloud providers the provider-bound copy is privacy-transformed by default
(LCM_EMBEDDING_PRIVACY_ENABLED=false opts out), while lcm.db keeps the raw text. Every turn (user, assistant and tool
output) is stored in plaintext in lcm.db (secret redaction at rest is opt-in). The engine also reads Hermes'' state.db
read-only for session lineage, reads private AIAgent attributes via the call stack on Hermes builds without subagent
hooks, and runs git on its own install directory for lcm_status/lcm_doctor; tiktoken may fetch its BPE file on first use.'
maintainer: electricsheephq
tier: community
category: memory
requires_hermes: '>=0.21.3'
docs_url: https://github.com/electricsheephq/lcm-x#readme
version: "0.24.1"
platforms: []
capabilities:
provides_tools:
- lcm_grep
- lcm_recall
- lcm_query_state
- lcm_compute
- lcm_compile_evidence
- lcm_evidence_pack
- lcm_retrieve
- lcm_recent
- lcm_load_session
- lcm_describe
- lcm_expand
- lcm_expand_query
- lcm_status
- lcm_inspect
- lcm_doctor
provides_hooks:
- pre_llm_call
- post_llm_call
- subagent_start
- subagent_stop
provides_middleware: []
requires_env: []