Awesome Hermes PluginsMemory Providers

esaradev/icarus-plugin

⭐ 147 Python added to this list on 2026-07-15 repository created 2026-03-30

Icarus is a Hermes Agent plugin designed to enhance agent capabilities by providing shared, cross-instance memory, enabling agents to remember their work and continuously improve. It facilitates the extraction of high-quality training data from agent decisions and actions, allowing for the development of tailored fine-tuned models. The plugin includes a comprehensive model replacement pipeline, supporting the training, evaluation, and eventual deployment of specialized agent models directly from the agent's historical performance. Key features include tools for ranked memory retrieval, writing entries with detailed linking and handoff fields, keyword-based searching across memories, and curating memory entries with decision-quality tags. It also provides tools for exporting training pairs, initiating fine-tuning jobs, tracking training status, and managing replacement models (listing, evaluating, switching, and rolling back). Furthermore, Icarus integrates four automatic hooks to manage session context, inject relevant memories, capture high-value decisions, and score session quality, ensuring continuous learning and adaptation without explicit agent calls. While it can be optionally integrated with Obsidian for viewing, it is not an Obsidian plugin itself, offering a self-contained memory and model management system for Hermes agents.

https://github.com/esaradev/icarus-plugin

Nous Research Hermes AgentHermes pluginself-memoryAI agent memorymodel trainingfine-tuningmodel replacementagent toolshooksdecision-quality taggingtraining data extractionmodel evaluation

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.