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
rarf/optmem-hermes-plugin
This project provides an OptMem memory provider plugin for Hermes Agent, offering a local, append-only, and decay-compressed memory solution. It's an independent reimplementation of Victor Taelin's OptMem design, ensuring byte-level compatibility with the original's on-disk format (`LOG.txt` and `TREE/`). Unlike cloud-backed memory providers, OptMem operates locally with zero dependencies (pure Python standard library), offering sub-millisecond latency and no per-call token costs. It supports native Windows with `msvcrt` advisory locks and features accent-normalized BM25 recall for efficient searching. The plugin integrates seamlessly into Hermes Agent as a `MemoryProvider`, exposing tools like `optmem_note`, `optmem_recall`, `optmem_nap`, and `optmem_wake`. It also mirrors builtin memory writes via `on_memory_write`, ensuring existing memory feeds into permanent recall without migration. The README highlights its advantages over cloud providers in terms of startup dependency, latency, cost, and data residency, positioning it as a complementary durable default for local memory storage alongside external providers for richer modeling.
https://github.com/rarf/optmem-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.