honcho

Configure cross-session memory and multi-profile user modeling for Hermes via Honcho.

Updated May 4, 2026
One-click install
npx skills add https://github.com/Plaidmustache/hermes-nulab --skill honcho-plaidmustache
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: honcho
Source: https://github.com/Plaidmustache/hermes-nulab/tree/main/optional-skills/autonomous-ai-agents/honcho
Command: npx skills add https://github.com/Plaidmustache/hermes-nulab --skill honcho-plaidmustache

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cross-session memory and multi-profile user modeling for Hermes are made possible with Honcho, enabling persistent user representations and separate AI peers across profiles.

Core Features & Use Cases

  • Cross-session user modeling with Honcho for Hermes
  • Per-profile AI peers sharing a unified workspace while keeping individual observations
  • Configurable observation toggles, recall modes, and session summaries
  • Dialectic controls, memory budgets, and per-profile config via honcho.json
  • CLI commands and tooling: honcho_profile, honcho_search, honcho_context, honcho_reasoning, honcho_conclude

Quick Start

Run Hermes honcho setup to enable Honcho for the active profile and begin configuring memory, sessions, and observation.

Frequently Asked Questions about honcho

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

FAQPage Schema
How do I set up cross-session memory for Hermes using Honcho?

To set up cross-session memory for Hermes using Honcho, run the Hermes honcho setup command to enable Honcho for the active profile. This initializes persistent user representations and begins configuring memory, sessions, and observation toggles.

What is multi-profile user modeling in AI peers?

Multi-profile user modeling creates separate AI peers that share a unified workspace while maintaining individual observations. This allows distinct persistent user representations across different profiles using Honcho's cross-session memory architecture.

Can I configure observation toggles and recall modes per profile?

Yes, you can configure observation toggles, recall modes, and session summaries per profile. Honcho supports per-profile configuration via the honcho.json file, allowing customized dialectic depth, memory budgets, and individual observation settings.

What CLI commands are available for Honcho memory management?

Honcho memory management provides CLI commands including honcho_profile, honcho_search, honcho_context, honcho_reasoning, and honcho_conclude. These tools handle profile configuration, memory search, context retrieval, and session reasoning operations.

Does Honcho support both cloud and self-hosted deployments for session summaries?

Yes, Honcho supports both cloud and self-hosted deployments for managing session summaries. You can configure memory management features, including observation toggles and dialectic depth, across either deployment type using the appropriate setup configuration.