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
btnalit/Hermes-Memory-OS
Hermes Memory-OS is a layered memory and cognition plugin for long-running Hermes Agent profiles that goes beyond retrieval to track whether an experience should become a durable belief at all. Its memory kernel keeps a canonical file store with working, provisional, and crystallized memory tiers; provisional records must pass evidence, clearance, stability and owner gates before becoming permanent, and contradictory memories stay visible through contested projections rather than being silently overwritten. Retrieval combines SQLite FTS5 full-text search, optional local vector similarity via sentence-transformers, and a bounded one-hop expansion through a dynamic memory graph, fused with reciprocal rank fusion and falling back safely to plain FTS5 when richer lanes are disabled. The memory graph grows on its own from four signals (structural analysis, provenance links, vector similarity, and a bounded LLM lane), assigns evidence-tiered birth weights, reinforces edges only when they are actually shown to the agent, and invalidates edges unused for 60 days, so the graph is expected to shrink as well as grow. An evidence and truth layer adds source gating, confabulation detection, and contradiction lanes; a cognition system (Inner Drive, Deep Reflection, Imagination Loop, Wandering Mind) and an expression system with rate-limited, judged output round out an optional right-brain module that can associate freely or stay silent without rewriting stored beliefs. Owner governance runs through the normal Hermes channel: review digests use stable oa_ action tokens that survive re-rendering, and every module can remain disabled, shadowed, or report-only until its evidence and owner gates justify a stronger mode. Requires Python 3.11+, MIT licensed.
https://github.com/btnalit/Hermes-Memory-OS
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.