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
benben17/hermes-d1-memory
This plugin integrates Cloudflare D1 (serverless SQLite) as a robust and scalable external memory provider for Hermes Agent. It enhances the agent's capabilities by offering semantic-like long-term memory, leveraging FTS5 for efficient full-text search. The design emphasizes zero-maintenance and edge-deployed persistence, making it highly suitable for agents requiring durable and fast memory access without complex infrastructure management. The plugin communicates with Cloudflare's D1 API purely via HTTP REST calls, avoiding heavy SDK dependencies and ensuring an extremely lightweight and fast operation. Key features include a durable local SQLite queue for memory writes, ensuring the agent never hangs while waiting for Cloudflare's API, and background flushing to D1. It also implements thread-safe prefetching of context, retry mechanisms with backoff for failed writes, and a structured schema for memories. The plugin automatically retrieves relevant durable memories to inject into the system prompt and provides explicit `d1_remember` and `d1_search` tools to the agent. It extends Hermes' built-in memory systems, ensuring `MEMORY.md` and `USER.md` remain active. Memories are isolated by user and agent but can be retrieved across agents for the same user, offering flexible scope management. Advanced configurations allow fine-tuning of background sync intervals, batch sizes, and prefetch limits.
https://github.com/benben17/hermes-d1-memory
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.