honcho

Configure Honcho memory for Hermes across sessions and profiles.

Updated Jun 15, 2026
One-click install
npx skills add https://github.com/faramirezs/talking_printer --skill honcho-faramirezs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: honcho
Source: https://github.com/faramirezs/talking_printer/tree/main/hermes-agent/optional-skills/autonomous-ai-agents/honcho
Command: npx skills add https://github.com/faramirezs/talking_printer --skill honcho-faramirezs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Honcho memory for Hermes enables AI-native cross-session user modeling by learning the user across conversations and giving every Hermes profile its own AI peer while sharing a unified view of the user.

Core Features & Use Cases

  • Cloud or self-hosted Honcho deployments for unified memory across sessions and per-profile AI peers.
  • Multi-profile setups where each profile has its own AI peer while sharing a common user representation.
  • Fine-grained configuration of observation, recall, and dialectic settings, along with context budgeting and session management.
  • Guided setup, troubleshooting, and per-profile customization via the Hermes Honcho CLI and honcho.json.
  • Clear usage patterns for starting conversations, updating memory, and aligning agents with shared workspace data.

Quick Start

Install Honcho memory, connect Hermes to your Honcho deployment, and run the setup to enable cross-session memory for all profiles.

Frequently Asked Questions about honcho

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enable cross-session memory for Hermes agents?

Enable cross-session memory for Hermes agents by connecting your Hermes deployment to Honcho and running the setup workflow via the Hermes Honcho CLI. This configures honcho.json to allow agents to learn user context across multiple conversations.

What is cross-session user modeling in AI memory profiles?

Cross-session user modeling is an AI memory mechanism that learns user behavior across different conversations. It gives every Hermes profile a dedicated AI peer while maintaining a unified, shared representation of the user.

Can I use a self-hosted Honcho deployment with multi-profile setups?

Yes, Honcho memory supports both cloud and self-hosted deployments for multi-profile setups. You can configure per-profile host blocks in honcho.json so each profile has its own AI peer sharing a common user representation.

How do I tune observation, recall, and dialectic settings for AI memory?

Tune observation, recall, and dialectic settings by adjusting parameters within the honcho.json configuration file. This allows fine-grained control over context budgeting and session management across your Hermes profiles.

Does Hermes integration require per-profile host blocks for Honcho memory?

Yes, Hermes integration with Honcho requires per-profile host blocks and memory-enable configuration in honcho.json. This structure ensures each profile correctly routes to its designated AI peer for cross-session recall.