---
author: "Mukul Chugh"
canonical: "https://mukulchugh.com/projects/hermes-memory"
description: "A dashboard plugin that makes Honcho agent memory explorable: relationship graphs, searchable facts, pipeline status, and questions about what an agent knows."
image: "https://mukulchugh.com/og/projects/hermes-memory.png"
language: "en"
title: "Hermes Memory"
type: "project"
---

# Hermes Memory

A dashboard plugin that makes Honcho agent memory explorable: relationship graphs, searchable facts, pipeline status, and questions about what an agent knows.

## Technology

Python, FastAPI, React, PostgreSQL

## See what the agent remembers.

Persistent agent memory becomes difficult to inspect when conclusions, relationships, and background processing are scattered across an API. Hermes Memory brings those views into the existing agent dashboard.

## How it works

- Inspect the memory pipeline and relationship graph
- Filter facts by peer, level, and search query
- Ask memory questions or request consolidation

## Implementation

A FastAPI router connects the dashboard to Honcho. The implementation can aggregate directly from PostgreSQL, with a paginated HTTP fallback. The frontend uses the host's React and UI primitives, while peers and relationship counts come from current memory rather than fixed examples.

## Scope and boundaries

The plugin depends on a configured Hermes/Honcho environment. Chat and dream scheduling are explicit write actions. Repository documentation and source differ on caching details, so no latency or scale guarantees are claimed here.

## Sources

- <https://github.com/mukulchugh/hermes-memory>
- <https://github.com/mukulchugh/hermes-memory/blob/main/dashboard/plugin_api.py>

[Repository](https://github.com/mukulchugh/hermes-memory)

---

[View this page](https://mukulchugh.com/projects/hermes-memory) · [Site index](https://mukulchugh.com/llms.txt)