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 ...
Awesome Hermes Plugins › Memory Providers
TencentDB Agent Memory is a sophisticated plugin designed for Nous Research Hermes Agent, offering a fully local long-term memory solution without external API dependencies. It introduces a innovative 4-tier progressive pipeline, leveraging symbolic short-term memory and layered long-term memory. The symbolic short-term memory offloads verbose tool logs, condensing them into compact Mermaid symbols, which significantly reduces token usage and boosts task success rates. The layered long-term memory system transforms fragmented conversations into structured personas and scenes, moving beyond flat vector storage. This architecture results in substantial improvements, such as up to a 61.38% reduction in token usage for certain benchmarks and a 51.52% increase in pass rates. The core technology emphasizes memory layering, with progressive disclosure and heterogeneous storage, and symbolic memory, utilizing Mermaid canvas to maximize semantics in minimal symbols. This ensures full traceability and lossless recovery, allowing agents to remember effectively and users to focus on higher-level tasks. The plugin is presented as an OpenClaw and Hermes compatible solution, aimed at addressing the inefficiency of repeated explanations to AI agents and enhancing their ability to learn and retain context across sessions.
https://github.com/TencentCloud/TencentDB-Agent-Memory
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 ...
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...
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 is a zero-dependency, sub-millisecond AI memory system for Hermes Agents and other LLM frameworks, focusing on efficient, local, and private knowledge retention.
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 ...
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.
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.
Open Second Brain provides an Obsidian-native, local-first memory layer for Hermes Agent, enabling deterministic learning and access across multiple AI runtimes.