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
yantrikos/yantrikdb-hermes-plugin
The yantrikdb-hermes-plugin provides a robust and advanced memory solution for Hermes Agent, leveraging YantrikDB's unique capabilities. It addresses common challenges of traditional vector-based memory systems by offering self-maintaining memory features, including canonicalization of duplicates, proactive hygiene, and the ability to surface and resolve contradictions. A key strength is its explainable recall, providing insights into why specific memories are retrieved. The plugin integrates agent-authored skills with an outcome ledger, distinct from Hermes's filesystem-based skills, and offers owner-scoping for multi-platform Hermes instances. It supports both an embedded in-process backend (default) for easy deployment and an HTTP backend for high-availability clusters. Notably, it features a self-tuning recall mechanism where reinforced memories gain prominence over time, and a 'self-directing loop' that allows the memory to identify knowledge gaps, queue tasks, and propose an agenda to the agent for resolution. This plugin is designed to be a drop-in replacement for or enhancement to existing memory providers, emphasizing durability, advanced temporal context management, and an ability to manage the lifecycle of information within the agent's knowledge base. It explicitly aims to solve problems like silent loss of constraints in long-running agents and the limitations of vector similarity alone for complex memory management.
https://github.com/yantrikos/yantrikdb-hermes-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.