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
MemoriLabs/Memori
Memori provides a comprehensive memory infrastructure designed for AI agents, enabling the transformation of agent execution and conversational data into structured, persistent states. It is built to be LLM, datastore, and framework agnostic, ensuring seamless integration with existing IT architectures without requiring a 'rip-and-replace' approach. Memori can be deployed across various environments, including managed cloud, single-tenant cloud, VPC, and on-premises setups. The core value proposition of Memori is to enhance agent performance by providing persistent, context-aware memory, thus preventing agents from 'forgetting' past interactions and decisions. It features a Python SDK for easy integration and offers explicit `memori_recall` and `memori_recall_summary` tools for agent-controlled recall within the Hermes ecosystem. The project also ships as a Hermes Agent memory provider, capturing completed conversations in the background and making them available to agents. Memori's performance is highlighted by its LoCoMo benchmark results, demonstrating high accuracy with efficient token usage, significantly reducing context footprint compared to full-context prompting. Beyond Hermes, Memori also provides integrations for OpenClaw and MCP (Connect Your Agent in One Command) to support other agent frameworks and development tools like Claude Code, Cursor, Codex, Warp, or Antigravity.
https://github.com/MemoriLabs/Memori
Also in Memory Providers
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.
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.