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
Signet-AI/signetai
Signet is a local-first memory and context layer that runs underneath existing agent harnesses instead of replacing them. It synchronizes memories, identity files, session transcripts and encrypted secrets across Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI, Pi, Hermes Agent, MCP clients, SDKs and custom applications, so context survives a change of model, provider or harness. Hermes Agent is supported through a connector plugin directory inside the repository integrations tree, installed under an existing Hermes setup rather than around it. Storage is a local SQLite database plus readable workspace files holding transcripts, source records, memories, optional identity files and encrypted secrets, all in a location the operator controls and can back up or move. Recall is source-backed: a useful memory can point back to where it came from, which is what makes the store auditable. Memory is explicitly repairable, so records can be inspected, edited, superseded, deleted, reclassified and re-scoped from a dashboard rather than being trapped behind a hosted recall response; the documented proof loop is to store a policy, recall it, then correct a stale entry and verify the agent sees the corrected context before it acts. For teams the project adds scoped agents, visibility rules, authentication policy, retention controls, secrets storage and audit-friendly APIs. The authors report a 97.6 percent average answer accuracy on the LongMemEval benchmark and describe the system as one of the few local-first implementations at that level. The project is explicit about the operating tradeoff: Signet is infrastructure, not a hosted shortcut, so the user runs a local or self-hosted daemon, chooses an embedding provider, backs up the workspace directory and connects harnesses through hooks, MCP, connectors or SDKs. Installation is a shell script followed by an interactive setup wizard, a status check and a dashboard command. It is Apache-2.0 licensed.
https://github.com/Signet-AI/signetai
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.