honcho

Configure cross-session AI memory with Honcho for persistent user modeling.

2|1|Updated Jul 14, 2026
One-click install
npx skills add https://github.com/heysuhas/hermes_cli --skill honcho-heysuhas
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: honcho
Source: https://github.com/heysuhas/hermes_cli/tree/main/optional-skills/autonomous-ai-agents/honcho
Command: npx skills add https://github.com/heysuhas/hermes_cli --skill honcho-heysuhas

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires honcho-ai.

What problem does it solve?

Honcho solves the problem of AI agents forgetting user preferences, context, and interaction history across different sessions, ensuring a consistent and personalized experience.

Core Features & Use Cases

  • Cross-Session User Modeling: Builds a persistent representation of user preferences and facts that evolves over time.
  • Multi-Profile Peer Isolation: Allows multiple AI profiles to share a workspace while maintaining independent identities and observation settings.
  • Dialectic Reasoning: Employs a multi-pass reasoning engine to synthesize complex user patterns and provide deeper, more accurate insights.

Quick Start

Use the honcho skill to initialize the memory system for the current project by running the setup command.

Frequently Asked Questions about honcho

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

FAQPage Schema
How do I enable persistent cross-session memory for an AI agent?

To enable persistent cross-session memory, you initialize the Honcho system within your project, which builds a continuous representation of user preferences and facts that survives across multiple sessions.

What is dialectic reasoning in the context of AI user modeling?

Dialectic reasoning in AI user modeling is a multi-pass synthesis engine that processes complex user patterns to generate deeper insights and maintain a continuously evolving representation of user context.

Can I isolate multiple AI profiles in a shared workspace environment?

Yes, you can isolate multiple AI profiles in a shared workspace using multi-profile peer isolation, which synchronizes peer identities, observation toggles, and context budgets while maintaining independent environments.

Do I need to install the honcho-ai package to use cross-session memory features?

Yes, you need to install the honcho-ai package because it facilitates the bidirectional tool-based memory access and system prompt injection required for cross-session user modeling.

How does an AI agent access stored user preferences during a session?

An AI agent accesses stored user preferences through bidirectional tool-based memory access, allowing the agent to read and write context dynamically via system prompt injection during active sessions.