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
eleboucher/memini
memini offers a robust and scalable persistent memory solution for AI agents, specifically compatible with the Model Context Protocol (MCP). It allows agents to robustly remember and recall information, with retrieval quality improving over time through tiered storage (working, episodic, semantic, procedural) and a sophisticated hybrid retrieval system combining vector and keyword search. The system uses Reciprocal Rank Fusion and re-ranks results based on relevance, access recency, and importance. Built in Go, memini runs as a single static binary, offering flexibility with storage options like embedded SQLite-vec or PostgreSQL with VectorChord. It supports external OpenAI-compatible embedding endpoints and can operate with or without an LLM configured for advanced consolidation and fact distillation. Integrations are provided for various agent frameworks, including a dedicated Hermes plugin. The project emphasizes operational ease with zero-configuration setup for basic use cases and offers comprehensive documentation for deployment, tuning, and understanding its underlying concepts. Benchmarks demonstrate its effectiveness in recall performance.
https://github.com/eleboucher/memini
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.