42-evey
evey-memory-consolidate
Nightly memory consolidation for Hermes agents — extracts facts into MEMORY.md and Qdrant vectors.
Repository last updated Jul 18, 2026
Overview
Evey Memory Consolidate is a plugin for the Hermes Agent ecosystem that automates the process of consolidating an agent's memories. It runs nightly, extracting key facts and insights from the agent's recent interactions and storing them in a structured format.
The plugin writes consolidated facts into a MEMORY.md file for easy human review and simultaneously indexes them as vector embeddings in a Qdrant database. This dual storage enables both readability and efficient semantic retrieval.
Designed for autonomous agents that accumulate large volumes of conversation history, this plugin helps maintain a concise, searchable long-term memory without manual intervention. It is ideal for developers building persistent AI agents that need to recall past decisions and knowledge.
Highlights
- Runs nightly to consolidate agent memories
- Extracts facts into human-readable MEMORY.md
- Stores vectors in Qdrant for semantic search
- Automates long-term memory maintenance
- Integrates with Hermes Agent plugin system
Features
Nightly Consolidation
Automatically runs on a schedule to process recent agent interactions and extract key facts.
Dual Storage Output
Writes consolidated facts to a MEMORY.md file and as vector embeddings in Qdrant for flexible retrieval.
Plugin-Based Integration
Seamlessly integrates into the Hermes Agent ecosystem via a standard plugin.yaml manifest.
Installation
Commands are reproduced exactly as published by the project maintainers. Always check the upstream repository for the current instructions.
git clone https://github.com/42-evey/hermes-plugins.git
cp -r hermes-plugins/evey-* ~/.hermes/plugins/
cp hermes-plugins/evey_utils.py ~/.hermes/plugins/
# Restart hermes-agentRequirements
- Hermes Agent installed and configured
- Qdrant vector database running and accessible
- Python 3.8+
How it's built
The plugin is structured as a standard Hermes Agent plugin with a plugin.yaml manifest and a Python package evey-memory-consolidate/. The main logic resides in __init__.py, which implements the consolidation routine.
It uses Qdrant as the vector database for storing embeddings, enabling fast similarity searches across consolidated memories. The MEMORY.md file is generated in the agent's working directory for easy inspection.
The plugin is written in Python and licensed under MIT. It is triggered by a scheduler (e.g., cron) or the Hermes Agent's internal scheduling mechanism, depending on configuration.
Source
This summary was written for Neura Market from the project's own repository. Install commands, identifiers and licence details are reproduced unchanged. The 42-evey/evey-memory-consolidate repository is the authoritative source and the place to file issues or contribute.
Category: Memory & Knowledge · Licensed under MIT