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
alejandroiglesias/hermes-dreaming
Hermes Dreaming is a specialized plugin designed to enhance the memory management capabilities of the Hermes self-improving AI agent. Recognizing that Hermes' durable memory (such as `MEMORY.md` and `USER.md`) is a limited and critical resource, this plugin implements a sophisticated background consolidation process. It operates in three distinct phases: Light, Deep, and REM. The Light phase scans recent agent sessions to identify potential facts and preferences. The Deep phase then analyzes these candidates to detect patterns, contradictions, and instances where newer information supersedes older data. Finally, the REM phase scores these candidates and, based on high confidence, applies a limited number of memory operations: adding new memories, replacing outdated ones, or removing irrelevant entries. The plugin is designed to prioritize future usefulness per character over simply accumulating more memories, meaning a run might result in zero durable writes if no significant improvements are identified. Memory mutations enacted by Hermes Dreaming take effect at the start of the next Hermes session. The plugin provides several command-line interfaces (`/dreaming run`, `review`, `status`, `compact`) for manual control and interaction, including a `compact` command to merge duplicates and remove obsolete items. It also supports scheduled execution via cron jobs and allows user configuration of its behavior, including enabling/disabling and setting the maximum number of changes per run. All runtime state and an audit diary are maintained in `~/.hermes/dreaming/` for transparency and debugging.
https://github.com/alejandroiglesias/hermes-dreaming
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.