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
The `scope-recall-hermes` repository provides a Nous Research Hermes Agent memory provider plugin, focusing on both transient current-turn recall and durable semantic memory. It allows Hermes to retain context across user sessions while isolating local scratchpad data. The plugin features a three-layer design: a journal/provenance layer for raw conversation turns, an authoritative SQLite truth store for durable records and auditing, and an optional vector companion (LanceDB by default, or SQLite for non-AVX hosts) for semantic retrieval and hybrid ranking. Key design principles include inspectable truth via SQLite, current-turn scoped recall, deliberate travel of durable memory across sessions for the same user/agent identity, and raw turns serving as provenance rather than durable memory. It ensures that operator actions fail closed for critical operations like cross-scope export or repair. The plugin is designed for practical installation, leveraging hosted embeddings when configured or deterministic local hashes for bootstrap. It distinguishes itself by providing robust memory management that includes background digestion, local scratch scopes, and hybrid RRF retrieval, making it a comprehensive solution for agents requiring advanced, durable, and context-aware memory capabilities.
https://github.com/410979729/scope-recall-hermes
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.
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 ...
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...
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 is a zero-dependency, sub-millisecond AI memory system for Hermes Agents and other LLM frameworks, focusing on efficient, local, and private knowledge retention.
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 ...
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.
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.