memex-hermes is an open-source Python package that connects the Hermes Agent to the memex unified-memory corpus, enabling a single searchable history across multiple agent platforms. Below are 6 frameworks & sdks apps with similar functionality to memex-hermes, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
hermes-brain-memory is an open-source memory provider for the Hermes Agent framework, offering local-first, cross-agent Markdown memory storage. It enables agents like Claude Code, Codex, and OpenClaw to share and persist memory in a unified format without runtime dependencies. Designed for developers building agent-native applications.
Agent 记忆系统 — 轻量级本地向量数据库 + CLI + Agent Skill
mnemosyne-hermes is an open-source memory provider designed for the Hermes Agent framework, offering local-first, zero-cloud long-term memory storage. It enables AI agent developers to integrate persistent, privacy-focused memory into their agents without cloud dependencies. The package is MIT licensed and CLI-accessible.
ultramemory-hermes is an open-source, self-learning long-term memory provider designed for Hermes Agent and any MCP-compatible client. It offers metamemory-gated memory management, private tenant isolation via API keys, and supports retrieval-augmented generation workflows. Ideal for developers building advanced AI agents requiring persistent memory.
hindsight-hermes is an open-source CLI tool that integrates Hermes agents with Hindsight, providing persistent memory capabilities for AI agents. It is designed for AI developers building autonomous agent systems that require long-term memory and context retention.
hermes-cashew is an open-source plugin that provides Cashew thought-graph memory capabilities to Hermes Agent frameworks. It enables persistent, structured memory for AI agents, enhancing their ability to retain and utilize context across interactions.
