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
aristoapp/hermes-membase
The hermes-membase plugin provides persistent long-term memory capabilities for Nous Research Hermes Agent. It integrates with Membase, a hybrid memory solution that combines vector search with a knowledge graph to store and retrieve not just text, but also entities, relationships, and facts. This enables the Hermes Agent to remember information across sessions, significantly improving its contextual awareness and consistency. The plugin offers several features for memory management, including 'Auto-Recall' that injects relevant memories into context before AI turns, 'Auto-Capture' for buffering and storing conversation transcripts in Membase Wiki, and 'Mirror Built-in' to automatically mirror Hermes's internal MEMORY.md writes to Membase for cross-session persistence. Unlike simple vector-only memory solutions, Membase's knowledge graph component allows for a richer and more structured understanding of stored information. It provides a suite of AI tools that agents can use autonomously, such as `membase_search` for semantic memory retrieval with filtering options, `membase_store` for saving important information, `membase_forget` for deleting memories, and `membase_profile` for retrieving user context. Additionally, `membase_search_wiki`, `membase_add_wiki`, `membase_update_wiki`, and `membase_delete_wiki` tools are available for managing structured wiki documents. The plugin also includes CLI commands for installation, authentication, status checks, and memory synchronization, making it easy to set up and manage.
https://github.com/aristoapp/hermes-membase
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.