Metronix adds self-hosted memory that can connect to Hermes
Metronix Core is a self-hosted memory tool for AI agents. It can pull information from Jira, Confluence, Notion, GitHub, Google Drive, Slack, and local files so an agent has more useful background to work with. It combines different search methods and a to find relevant material, and it can provide .
Its memory is split into facts, preferences, and pinned items, with separate scopes for each workspace and agent. It also checks for stale or conflicting facts, which is meant to reduce confident wrong answers. It can connect to Cursor, , Claude Code, Hermes, and Open WebUI.
It can run locally with Ollama, so an outside is not required. The stack uses Python, PostgreSQL, Qdrant, Neo4j, and Redis, and it runs as one setup under the .
Key points
- Metronix Core can connect to Hermes as a memory layer for AI agents.
- It imports data from workplace tools like Notion, GitHub, Google Drive, Slack, and local files.
- It stores different memory types, including facts, preferences, and pinned items.
- It flags stale or conflicting information to reduce wrong answers.
- It can run locally through Ollama and .