Awesome Hermes PluginsMemory Providers

tuancookiez-hub/HyAtlas-Memory

⭐ 23 Python added to this list on 2026-07-15 repository created 2026-06-11

The HyAtlas-Memory plugin integrates a sophisticated long-term memory stack into Hermes Agent, enabling persistent and structured memory across sessions. It is a personal, local, single-user system derived from the Tencent Hunyuan Hy-Memory 7-layer cognitive memory framework, adapted for individual use. This plugin allows Hermes Agent to retain knowledge about user preferences, project structures, coding conventions, and past decisions beyond typical short-term memory limits. The system automatically captures conversations, extracts atomic facts, resolves conflicts, and builds a knowledge graph across its seven memory layers. Relevant memories are automatically injected into the agent's context during new interactions without manual intervention. Over time, background processes refine the agent's understanding by merging duplicates, resolving contradictions, and stabilizing a long-term identity profile. Key features include an experimental L7 intention layer, emotion-aware memory strength, reasoning model support, and a comprehensive dashboard for visualization and management. The plugin also forks the entire hy-memory codebase, eliminating external dependencies and allowing for single-user optimization. It supports various operational modes (lite, pro, ultra) and uses Zvec as its default in-process vector store provider, with an option for legacy Qdrant users. This plugin significantly enhances Hermes Agent's ability to maintain context and evolve its understanding of the user over extended periods.

https://github.com/tuancookiez-hub/HyAtlas-Memory

Hermes Agentpluginmemory providerlong-term memoryHy-Memorycognitive frameworkknowledge graphpersonal AIlocal agentZvec

Also in Memory Providers

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.

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.