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
mnemosyne-oss/mnemosyne
Mnemosyne provides a universal memory layer designed for AI agents, with a 'Hermes-first' approach but compatible with various agent frameworks like Claude Code, Cursor, Codex, and OpenAI's OpenWebUI. It operates with zero external dependencies, utilizing a single SQLite database for all memory operations, ensuring high performance (sub-millisecond recall) and data locality. The system offers multiple levels of memory: Working Memory, Episodic Memory, and a Triple Store for knowledge graphs, all integrated through its BEAM architecture. Mnemosyne can be integrated via its Python SDK, a CLI, or as an MCP (Model Context Protocol) server, making it versatile for different agent setups. A key feature is its included 23-tool Hermes Plugin, enabling native integration and extending agents' capabilities with robust memory management, including facts, preferences, temporal data, and entity extraction. It emphasizes security and privacy, storing all data locally and optionally encrypted, distinguishing it from cloud-dependent memory solutions. The project also highlights its high performance on AI memory benchmarks like LongMemEval and BEAM.
https://github.com/mnemosyne-oss/mnemosyne
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.
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.
itechmeat/open-second-brain
Open Second Brain provides an Obsidian-native, local-first memory layer for Hermes Agent, enabling deterministic learning and access across multiple AI runtimes.