# stephenschoettler/hermes-lcm

Lossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message

Repository: https://github.com/stephenschoettler/hermes-lcm
Canonical: https://ross.abutalabs.com/products/hermes-lcm
Language: Python
License: MIT
License Family: permissive
Last push: 2026-09-02T20:40:04+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 94, longevity 10
- inputs: {"age_days": 149, "days_push": 0, "days_rel": 40, "gap_med": 1.0, "n_releases_24m": 35}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1102, forks 121 (observed 2026-09-03T02:15:18.141144+00:00)

## What it is
A lossless context management plugin for Hermes Agent that replaces one-shot prompt compression with a SQLite-backed, DAG-based context engine. It keeps the live prompt bounded while preserving every raw message and providing recall tools so agents can search and expand compacted context on demand.

## Use cases
- keep agent conversations from losing details when context is compacted
- give my AI agent long-term memory without unbounded prompts
- search and recover exact past messages after summarization
- build hierarchical summaries of long agent sessions
- import lossless-claw context into Hermes Agent

## When to avoid
- you don't use Hermes Agent or a compatible host
- you need a general-purpose vector database or RAG framework
- you want a hosted or language-agnostic memory service

## Facets
- artifact type: plugin
- maturity: active
- function: rag, search-engine, database, llm-inference
- domain: large-language-models, databases, developer-tools
- platform: python, cli
- tags: context-management, agent-memory, sqlite, dag, hermes-agent, lossless-compaction, conversation-recall, ai-agents

## Member repositories
- stephenschoettler/hermes-lcm (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:18.141144+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:53:33.435500+00:00, confidence not recorded.
  - readme: https://github.com/stephenschoettler/hermes-lcm (fetched 2026-09-03T02:15:18.141144+00:00, sha a5b750af9f9a)
- Data as of 2026-08-30T08:39:29.467469+00:00.