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
aliyun/hermes-tablestore-memory
The `aliyun/hermes-tablestore-memory` project offers a robust external memory provider for Hermes Agent, leveraging Alibaba Cloud's TableStore service. This plugin enables Hermes to utilize TableStore as a backend for semantic long-term memory, complementing the agent's built-in memory stores. Key features include automatic synchronization of completed conversation turns to TableStore, intelligent prefetching of relevant memories for upcoming turns, and explicit memory management tools for inspecting, searching, storing, and deleting facts. The plugin provides CLI commands such as `tablestore_profile` to list memories, `tablestore_search` for semantic retrieval, `tablestore_remember` to persist information, and `tablestore_forget` to delete entries. It also mirrors Hermes's internal memory writes into TableStore for comprehensive record-keeping. Installation is straightforward via `hermes plugins install` or manual copying, with clear instructions for managing Python dependencies. Configuration involves environment variables for sensitive credentials (Access Key ID and Secret Key) and a `tablestore_memory.json` file for other settings like memory store name, application ID, and instance details. The plugin intelligently handles TableStore instance creation and endpoint resolution on first use. Memory scope is managed hierarchically (`appId/tenantId/agentId/runId`), ensuring precise attribution for writes and broad search capabilities across agents and sessions for a given tenant. Compatibility with Hermes Agent v0.10.0 or newer is required, along with specific Alibaba Cloud Python SDKs. The project emphasizes ease of setup, provides `doctor` commands for verification, and outlines how to activate and configure the memory provider, making it a valuable extension for users requiring scalable, persistent memory solutions in an Alibaba Cloud environment.
https://github.com/aliyun/hermes-tablestore-memory
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.