honcho

Configure and troubleshoot Honcho cross-session memory for ZeusAgent profiles.

Updated Sep 10, 2026
One-click install
npx skills add https://github.com/loteiron/ZeusAgent --skill honcho-loteiron
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: honcho
Source: https://github.com/loteiron/ZeusAgent/tree/main/optional-skills/autonomous-ai-agents/honcho
Command: npx skills add https://github.com/loteiron/ZeusAgent --skill honcho-loteiron

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires honcho-ai.

What problem does it solve? Setting up and maintaining persistent, cross-session user memory in ZeusAgent is complex: peers must be configured per profile, observation and recall modes tuned, and dialectic reasoning costs controlled. This Skill provides the operational knowledge to configure, tune, and debug Honcho memory so agents retain user context across conversations. ## Core Features & Use Cases - Setup & Verification: Guides cloud (app.honcho.dev) or self-hosted Honcho installation via zeus memory setup honcho and validates with zeus honcho status. - Multi-Profile Peer Management: Creates isolated AI peers per ZeusAgent profile with zeus profile create <name> --clone and backfills existing profiles using zeus honcho sync. - Dialectic Tuning: Explains the three orthogonal knobs—cadence, depth, and reasoning level—for controlling how often and how hard Honcho's dialectic engine works. - Tool Usage Patterns: Documents the 5 Honcho tools (honcho_profile, honcho_search, honcho_context, honcho_reasoning, honcho_conclude) and when to call each. - Use Case: A user notices memory is not persisting across sessions; the Skill directs them to check zeus honcho status, verify saveMessages: true, and confirm writeFrequency is not set to session. ## Quick Start Ask the agent to run zeus honcho status and walk you through setting up Honcho cloud memory for your current ZeusAgent profile.

Frequently Asked Questions about honcho

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

FAQPage Schema
How do I set up Honcho memory with ZeusAgent?▼

Run zeus memory setup honcho and choose cloud (paste an API key from app.honcho.dev) or local (enter a self-hosted base URL). Verify the connection and resolved configuration with zeus honcho status.

How do I give each ZeusAgent profile its own Honcho peer?▼

Create profiles with zeus profile create <name> --clone, which adds a host block, sets aiPeer to the profile name, and inherits shared settings. For existing profiles, run zeus honcho sync to backfill missing host blocks.

What is the difference between Honcho hybrid, context, and tools recall modes?▼

Hybrid (default) auto-injects context and exposes the 5 Honcho tools. Context mode auto-injects only, hiding tools to minimize token cost. Tools mode disables auto-injection so the agent controls all memory access explicitly.

Why is Honcho memory not persisting across sessions?▼

Check zeus honcho status and confirm saveMessages is true and writeFrequency is not set to session, which only writes on exit. Also verify memory.provider is honcho in ~/.zeus/config.yaml.

When should I use honcho_reasoning versus honcho_search?▼

Use honcho_search for fast, no-LLM retrieval of specific past facts as raw excerpts. Use honcho_reasoning only when you need a synthesized answer from Honcho's dialectic engine, since it incurs an LLM call and higher cost.

Does Honcho support self-hosted deployments?▼

Yes. During setup select local and provide the base URL of your self-hosted Honcho instance, such as http://localhost:8000. Configuration is stored in honcho.json with the baseUrl key.