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
agentscope-ai/ReMe
ReMe is a local-first personal knowledge base for AI agents that stores memory as ordinary Markdown files with frontmatter and wikilinks, so that both the user and the agent can read, edit, move and back up the same workspace. Auto Memory, Auto Resource and Auto Dream progressively turn conversations and ingested resources into daily notes and longer-lived knowledge, while Auto Link writes relationships and sources back into the files. Retrieval is hybrid and progressive: wikilink traversal, BM25 keyword matching and optional embedding search combine so that neighbouring files are not pulled into context wholesale. Embeddings are disabled by default, and basic file operations, BM25 search and wikilink traversal run without any LLM credentials, while the automatic evolution workflows require an LLM API key. The service starts with reme start on 127.0.0.1:2333 and exposes HTTP, MCP, CLI and Python integrations, plus an optional Studio web interface for browsing, editing and searching the workspace. The repository carries per-agent integrations under a plugins directory, including a hermes_agent plugin with a Hermes manifest and Python entry point, alongside a Claude Code plugin and SKILL.md based integrations for other agents. Documented use cases are a user-editable long-term memory layer for personal assistants such as Hermes, QwenPaw and OpenClaw; preserving coding style, project background and repository decisions across sessions for coding agents; a searchable and traceable Markdown wiki built from conversations, notes and resources; and self-evolving agents that store successful paths, failed attempts, reusable procedures and periodic reflections. Python 3.11 or newer is required and the package is published on PyPI as reme-ai. The project descends from MemoryScope and has associated ACL Findings and arXiv publications on procedural memory for experience-driven agent evolution.
https://github.com/agentscope-ai/ReMe
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...
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.