# OpenLTM — long-term memory for Hermes agents. # # Source of truth: https://github.com/RohiRIK/OpenLtm # Plugin lives in the `hermes/openltm_hermes` subdirectory of that repository. # The `sha` above is the exact reviewed commit; the version label matches it. name: openltm repo: https://github.com/RohiRIK/OpenLtm sha: 8ee2a8e4f9de60fcf16b37e0ea9c02c4d389ba35 subdir: hermes/openltm_hermes description: "Long-term memory for Hermes agents, stored in a local SQLite database. FTS5 full-text search with optional vector (sqlite-vec) recall, importance-weighted decay, a queryable memory graph, and automatic capture: a declarative rule engine classifies corrections, constraints, preferences, decisions, and agent-discovered facts from a conversation and stores each one as a distilled, self-contained fact. Runtime notifications and read-only OpenLTM tool requests are excluded by named guards so ops noise never becomes memory. No cloud, no telemetry, no API keys required; optional semantic recall via a local llama.cpp embedding server. MIT licensed. Disclosure — local SQLite in HERMES_HOME; runs git config to read the repo remote; memory text goes to Gemini or OpenAI embeddings, or to the llama.cpp server URL you set (default 127.0.0.1:8080), only if selected in openltm.json (default local Ollama)" maintainer: RohiRIK tier: community category: memory docs_url: https://github.com/RohiRIK/OpenLtm/blob/main/docs/10-hermes-plugin.md version: "2.21.1" image: https://raw.githubusercontent.com/RohiRIK/OpenLtm/8ee2a8e4f9de60fcf16b37e0ea9c02c4d389ba35/hermes/plugin-catalog/banner.png readme: true platforms: [] capabilities: provides_tools: - openltm_recall - openltm_learn - openltm_forget - openltm_context - openltm_relate - openltm_graph - openltm_brain_stats - openltm_stale provides_hooks: - system_prompt_block - prefetch - sync_turn - on_turn_start - on_session_switch - on_session_end - on_memory_write provides_middleware: [] requires_env: []