volcengine/OpenViking
A full bidirectional MemoryProvider plugin bringing OpenViking's viking:// context database — tiered retrieval, automatic session-end extraction, and semantic search — to Hermes Agent.
Awesome Hermes Plugins › Memory Providers
outpoints/hermes-honcho-plugin
Honcho Memory for Hermes is an independent, community-made Hermes Desktop plugin for Honcho (honcho.dev), a memory service that derives conclusions about a user from conversation. It is not affiliated with Nous Research or Plastic Labs. It opens as both a sidebar page and a docked pane beside the active chat, following whichever chat is in focus, and shows the connection, Hermes profile, mapped Honcho session and peer at all times so it is clear whose memory is being read. Its "Memory" view lists a session's conclusions newest-first with semantic search and the option to view a conclusion's premises and what was derived from it; "Ask" sends a question to Honcho at a chosen reasoning effort, scoped to the current session or all sessions, and on supported servers lists which records Honcho consulted; "Messages" shows saved messages grouped by day with search across the session, user or workspace; "Context" previews what Honcho would supply right now at a chosen token budget; and "Status" surfaces the connection, configuration and background-reasoning queue state. Two explicit, confirmation-gated actions can write to Honcho: "Add fact"/"Add correction" append one attributed conclusion without deleting or overwriting anything, and "Add to session" sends pasted text or an uploaded file into the session, which Honcho may split into multiple messages. The plugin requires Hermes 0.21.4+ with Hermes Desktop, the Honcho provider installed and configured per profile, and specific versions of the `honcho-ai` Python SDK; features the connected server or SDK version does not support are shown as unavailable rather than left blank. Remote SSH and gateway-connected profiles are supported as long as the plugin backend is installed on the remote profile, and a chat is never read through a profile other than its own.
https://github.com/outpoints/hermes-honcho-plugin
Also in Memory Providers
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.
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.