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
jasonatgit/echomind_memory.skill
EchoMind is a long-term memory engine that integrates with Hermes Agent as a MemoryProvider plugin and with OpenClaw, OpenCode, Claude Code and DeepSeek Haeness through skill definitions, an HTTP API or MCP. Storage is a single SQLite file with no Docker, PostgreSQL or Redis dependency, managed by a structured migration list with transactional writes. It distinguishes seven memory types, namely user, task, experience, context, knowledge, research and reflection, and layers reasoning on top of them. A self-evolving engine agent distils semantic knowledge and procedural rules out of raw memories and discards low-confidence reflections; an Ebbinghaus forgetting curve downranks or excludes stale records; a lifecycle state machine moves entries between active, stale, archived and superseded; and knowledge evolution tracking classifies new entries as replacing, enriching, confirming or challenging earlier ones through a hybrid Jaccard and LLM check. Every knowledge entry carries an epistemic mode recording whether it was user-provided, reasoned, fuzzy or merely referenced, resolved at write time without an LLM call, and a provenance chain records the originating agent, session and turn. Retrieval combines keyword matching, reinforcement-tuned weights adjusted from user feedback with cosine learning-rate decay and epsilon-greedy exploration, and LLM semantics. Preference inference covers code style, response style, platform, language, depth and tone, and correction phrases in Chinese or English trigger immediate reflection. Memory is isolated by user, project, session, topic and domain, with cross-platform matches downweighted. For Hermes it registers through a root register entry point with a manifest of kind exclusive, claims compatibility from v0.13 through v0.20, and injects a compact Markdown memory-context block on every turn with automatic save and retrieve and no LLM decisions. A nine-section Markdown dossier export and an aggregated memory health report are also provided.
https://github.com/jasonatgit/echomind_memory.skill
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.