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
volcengine/OpenViking
OpenViking is a large open-source context database for AI agents (38k+ stars) that organizes agent knowledge as a virtual filesystem under viking://, letting agents browse, read, write, and search content with ls/tree/read/write-style operations and on-demand directory summaries. Within its examples/hermes-plugin directory the project ships a complete, installable MemoryProvider plugin for Hermes Agent: openviking/__init__.py implements the full bidirectional MemoryProvider interface used by Hermes's memory system, includes a plugin.yaml manifest declaring the on_session_end hook and a pip dependency, and an interactive setup wizard (_setup.py) for configuring the OpenViking endpoint, API key, account, user, and agent identifiers via environment variables or a linked OpenViking CLI config. The plugin gives Hermes tiered context — an L0 abstract, L1 overview, and L2 full-detail representation — automatic memory extraction triggered on session commit, and semantic search over what the agent has stored, all backed by OpenViking's own context-database service (self-hostable or hosted via Railway). The repository publishes benchmark results comparing agents with and without OpenViking's memory, including a Hermes-specific LoCoMo evaluation showing a jump from roughly 33% to 83% accuracy, a companion Studio playground for browsing stored context, and the same integration pattern for other agent runtimes. The Hermes plugin directory itself includes its own DEVELOPMENT.md, pyproject.toml, and test suite, and imports Hermes's internal MemoryProvider base class and secret-scope helpers directly, making it a first-class rather than superficial integration. Runtime behavior, network calls to the OpenViking service, and security posture should be reviewed independently; the plugin needs network access to an OpenViking endpoint rather than running fully offline.
https://github.com/volcengine/OpenViking
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.