TencentCloud/TencentDB-Agent-Memory
TencentDB Agent Memory is a Hermes Agent plugin providing a 4-tier progressive and local-first memory pipeline to enhance AI agents by reducing token usage and improving task success rates.
Awesome Hermes Plugins › Memory Providers
Ladybug-Memory/hermes-memory-plugin
This project provides a standalone Hermes memory-provider plugin that integrates Ladybug Memory, a columnar embedded graph database, to offer a fully local, file-based memory store for the Hermes Agent. It allows for the storage of all data in a single `.lbdb` file within `HERMES_HOME`, ensuring no external API keys, cloud services, or sync are required. The plugin offers features such as BM25 keyword search, importance-weighted recall, typed memory entries, and named graph edges between entries. Optionally, it supports GLiNER2 for entity extraction. It is designed for users who prioritize local, inspectable memory with structured recall and graph relationships, avoiding SaaS dependencies. The plugin includes a suite of tools for persisting, searching, recalling, updating, deleting, linking, and querying memories, along with deep integration for background prefetching and automatic mirroring of built-in memory writes. Configuration options are available for database path, prefetch limits, and importance thresholds. This plugin serves as a robust alternative to cloud-based or less structured local memory solutions for Hermes Agent.
https://github.com/Ladybug-Memory/hermes-memory-plugin
Also in Memory Providers
MemoriLabs/Memori
Memori is an agent-native memory infrastructure, offering an LLM-agnostic layer that converts agent execution and conversation into structured, persistent state for production systems, including a ...
basicmachines-co/basic-memory
Basic Memory is a local-first, knowledge graph-based memory system for AI agents, providing persistent, bidirectional knowledge access via Markdown files and the MCP protocol, including a Hermes pl...
agentscope-ai/ReMe
A local-first Markdown memory service with a Hermes Agent plugin that turns conversations and documents into linked, searchable notes using wikilinks, BM25 and optional embedding retrieval.
mnemosyne-oss/mnemosyne
Mnemosyne is a zero-dependency, sub-millisecond AI memory system for Hermes Agents and other LLM frameworks, focusing on efficient, local, and private knowledge retention.
ClaudioDrews/memory-os
Memory OS is a 7-layer memory operating system for Hermes Agent, providing persistent memory, structured facts, fabric recall, an auto-curated wiki, and surgical context injection, running locally ...
zhangfengcdt/memoir
Memoir is a high-performance semantic memory system for AI agents, offering Git-like version control for AI memory management to combat context contamination, token costs, and memory drift.
MaxFreedomPollard/Compartment
Offline, encrypted agentic memory vault that installs into Hermes Agent as a plugin and MCP server, keeping one transferable memory store shared by every agent on the machine.