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
engrammemory-labs/engram-lite
engram-lite is a lightweight, local memory system designed for AI agents, distinguishing itself by offering conditioned serving based on agent persona, domain, and task. Unlike shared memory approaches, engram-lite prevents agents from hallucinating by providing only relevant information, significantly boosting task success rates. The system operates without relying on LLMs for memory operations, ensuring zero cost for memory building and improved determinism. Key features include conditioned serving, allowing the same query to yield different results based on the agent's profile, and restart-proof persistence via a single SQLite file. It also incorporates self-cleaning mechanisms, a salience gate to filter out junk, de-duplication, and expiration of stale facts. The project emphasizes zero infrastructure, offering easy installation via pip. Notably, engram-lite offers explainable forgetting, recording the rules for every memory decision, enabling transparent debugging. It integrates seamlessly with Hermes Agent as a memory provider, allowing agents to automatically capture turns, boot with snapshots of knowledge, and utilize in-loop tools like `memory_search` and `memory_write`. It also provides integrations for Claude Code and OpenClaw, enabling shared memory stores while maintaining individual agent lanes. The project includes benchmarks demonstrating its efficiency and effectiveness in long-conversation memory scenarios.
https://github.com/engrammemory-labs/engram-lite
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.