honcho

Configure and orchestrate Honcho memory for cross-session user modeling in Argo.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/nadicodeai/argo-agent --skill honcho-nadicodeai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: honcho
Source: https://github.com/nadicodeai/argo-agent/tree/main/optional-skills/autonomous-ai-agents/honcho
Command: npx skills add https://github.com/nadicodeai/argo-agent --skill honcho-nadicodeai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Honcho provides AI-native cross-session user modeling. It learns who the user is across conversations and gives every Argo profile its own peer identity while sharing a unified view of the user.

Core Features & Use Cases

  • Cross-session memory: per-profile AI peers share a workspace but maintain individual observations and representations.
  • Flexible recall and context: supports hybrid/context/tools modes, session budgets, and observation controls to tune memory.
  • Multi-profile management: create per-profile Honcho peers and sync configurations across profiles.

Quick Start

Run argo honcho setup to connect your Argo instance to Honcho (cloud or self-hosted), then verify with argo honcho status.

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 AI profiles?

Cross-session memory is enabled by configuring Honcho to model users across conversations. You run `argo honcho setup` to connect your instance, allowing per-profile peers to maintain individual observations while sharing a unified user view.

What is cross-session user modeling for AI peers?

Cross-session user modeling learns who the user is across multiple conversations. It gives every Argo profile an isolated peer identity while sharing a unified representation of the user within a workspace.

Can I use a self-hosted deployment for cross-session memory?

Yes, cross-session memory supports both cloud and self-hosted deployments. You can connect your preferred instance to Argo using `argo honcho setup` and verify the connection with `argo honcho status`.

How do I tune recall modes and context budgets for AI memory?

You tune AI memory by adjusting observation controls, session budgets, and recall modes. Honcho supports hybrid, context, and tools modes to configure how context is injected and recalled per profile.

Does cross-session memory work on a per-directory or per-repo basis?

Yes, cross-session memory can be configured for per-directory or per-repo sessions. This enables isolated AI peers and persistent user representations specific to individual project contexts.