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
Mugen0815/hermes-cortex
hermes-cortex gives Hermes Agent a plugin-managed, Obsidian-style Markdown vault as a long-term knowledge store, distinct from Hermes's own MEMORY.md, USER.md and SOUL.md files, which it explicitly does not replace or mutate by default. It indexes vault notes and exposes hybrid retrieval - BM25 keyword search, vector embeddings (via a local Chroma store) and wikilink-graph expansion fused with reciprocal rank fusion - through three agent-facing tools, vault_search, vault_read_note and vault_build_context (the last one assembling a cited Markdown context blob under a token budget), plus a full operator CLI for indexing, embedding, graph-building, validation and lifecycle maintenance. Installation clones the plugin into the Hermes plugins directory, enables it as both a plugin and a toolset, and runs an install script that can also set up a dedicated virtualenv and Hermes-facing skills; the init command then creates config and vault folders (including llm-wiki-compatible scaffolding like a schema file, an index file and a raw-material tree), seeding the vault path as the one durable configuration value that all later commands use - never a WIKI_PATH environment variable, which init only checks for alignment and reports as unset, aligned or mismatched without ever writing it. Lifecycle commands cover on-demand maintenance (index, embed, and graph build together), a dry-runnable nightly inbox promotion and cleanup, and a read-only weekly review report, with cron install and status commands to schedule the recurring ones. Cortex ships CI, an MIT license, and a documented architecture and CLI reference. It targets Hermes users who already keep a Markdown or Obsidian vault of notes and want the agent to search and cite it directly, rather than relying on Hermes's own short-form memory files or a hosted memory service.
https://github.com/Mugen0815/hermes-cortex
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.