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
r0b0tlab/hermes-zvec-memory
hermes-zvec-memory is a memory provider plugin for Hermes Agent that stores facts and session logs as Markdown under a profile-scoped vault ($HERMES_HOME/zvec-memory/), indexed by the zvec-grep (zg) CLI. Each turn, a prefetch step runs a hybrid BM25-plus-vector query (skipped for trivial prompts) and injects compact path:line results into context; a background sync step appends the turn to the daily session log and debounces reindexing (default 600 seconds) rather than reindexing per turn. The plugin exposes two tools, memory_search (hybrid, full-text, or vector search with globs and a result limit) and memory_store (append a fact with background reindex), and mirrors the built-in memory tool's writes into the vault; hermes backup automatically includes the vault. Installation copies the plugin directory into the Hermes plugins folder and activates it through hermes memory setup, which switches the active memory provider for all future sessions. The default embedding model is a small local model (potion-retrieval-32m), cached after first use; a larger local or remote embedding model can be configured, with remote (Qwen) embeddings requiring an explicit credential and permission grant since they send vault or query text off-machine. A bundled measure_recall.py script benchmarks hybrid versus full-text recall against paraphrased and same-vocabulary query sets, and the README documents concrete hit-rate and latency numbers showing prefetch is roughly 265x faster when warm. The project ships unit tests and credits the zvec-ai/zvec-grep retrieval engine (Apache-2.0); the plugin itself is MIT licensed.
https://github.com/r0b0tlab/hermes-zvec-memory
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.