honcho

Name: honcho
Availability: InStock
Author: eddielueng

Configure Honcho memory for cross-session user modeling in Hermes.

1|Updated Apr 14, 2026

Search Tags:#memory #context-injection #agent-configuration #multi-profile #user-modeling #dialectic-reasoning #recall-modes

Ready to run

npx skills add https://github.com/eddielueng/hermes-agent-zh --skill honcho-eddielueng

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: honcho
Source: https://github.com/eddielueng/hermes-agent-zh/tree/main/optional-skills/autonomous-ai-agents/honcho
Command: npx skills add https://github.com/eddielueng/hermes-agent-zh --skill honcho-eddielueng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Honcho Memory solves the problem of losing continuity across conversations by building a persistent, cross-session model of who the user is and applying it consistently to each Hermes profile.

Core Features & Use Cases

Cross-session user modeling: Maintains a user representation across turns and sessions so Hermes can tailor responses over time.
Multi-profile isolation with shared understanding: Gives each Hermes profile its own AI peer identity while sharing the unified user context across profiles.
Configurable observation + recall modes: Lets you tune what is learned (observe user vs observe others) and how memory is used (hybrid, context, or tools).
Dialectic reasoning controls: Supports tuning cadence, depth, and reasoning level to balance quality vs cost for synthesized memory-based answers.
Context budget enforcement: Prevents prompt bloat by trimming lower-priority parts (e.g., summary/representation) when exceeding configured token budgets.

Quick Start

Run honcho setup for cloud and follow the prompts to paste your API key from app.honcho.dev.

Frequently Asked Questions about honcho

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

FAQPage Schema

How do I maintain consistent user context across multiple agent sessions?▼

Cross-session user context is maintained by building a persistent user model that represents who the user is and applying it consistently to each agent profile. This prevents losing conversational continuity across turns.

How do I configure Honcho memory for user modeling in my agent setup?▼

Configuring Honcho memory requires installing the honcho-ai package, running honcho setup to input your API key, and defining memory provider settings in your honcho.json host configuration. This enables consistent user representation.

Can I isolate user memory for different agent profiles while sharing context?▼

Multi-profile isolation allows each agent profile to maintain its own AI peer identity while sharing a unified user context across all profiles. This ensures tailored responses without cross-profile interference.

What recall modes are available for tuning memory usage in context injection?▼

Available recall modes include hybrid, context, and tools modes. These control how memory is applied during context injection, letting you tune what is learned and how synthesized memory is used.

How do I prevent prompt bloat when injecting cross-session memory into context?▼

Context budget enforcement prevents prompt bloat by trimming lower-priority memory components, such as summary or representation data, when exceeding configured token budgets. This keeps context injection efficient.

What settings control dialectic reasoning quality and cost for memory synthesis?▼

Dialectic reasoning controls allow tuning cadence, depth, and reasoning level to balance answer quality against cost. These settings manage how memory-based answers are synthesized during recall.