honcho

Configure Honcho memory for Hermes across sessions and profiles.

Updated Apr 16, 2026
One-click install
npx skills add https://github.com/jacardl/New-Radar --skill honcho-jacardl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: honcho
Source: https://github.com/jacardl/New-Radar/tree/main/backend/frameworks/hermes-agent/optional-skills/autonomous-ai-agents/honcho
Command: npx skills add https://github.com/jacardl/New-Radar --skill honcho-jacardl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Honcho provides AI-native cross-session user modeling. Hermes assigns each profile its own AI peer while sharing a unified user view, enabling memory across sessions and better multi-profile reasoning.

Core Features & Use Cases

  • Cross-session memory with per-profile isolation for Hermes agents.
  • Adjustable observation toggles, recall modes, and per-profile configurations.
  • Troubleshooting memory issues and tuning memory performance for cloud or self-hosted setups.

Quick Start

Run hermes honcho setup to configure memory provider, observations, and recall settings for your active profile.

Frequently Asked Questions about honcho

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

FAQPage Schema
How does cross-session memory work for multi-profile Hermes agents?

Cross-session memory is enabled by assigning each profile its own AI peer while sharing a unified user view, allowing Hermes agents to recall context across sessions with per-profile isolation.

How do I configure Honcho memory provider and recall settings?

Run the Honcho setup command to configure the memory provider, toggle observations, and adjust recall settings for your active profile across cloud or self-hosted setups.

Can I use a self-hosted Honcho setup for per-profile session mapping?

Yes, this memory configuration applies to both cloud and self-hosted Honcho setups, supporting per-profile configuration, session mapping, and peer identity assignment for your agents.

What is the best way to isolate memory observations across different agent profiles?

The best way to isolate memory is using per-profile configurations with adjustable observation toggles, ensuring each AI peer maintains independent recall while contributing to a unified user view.

Why is my Honcho recall not working across sessions in Hermes?

Recall issues often stem from incorrect session mapping or dynamic recall mode settings; troubleshooting involves verifying your peer identity configuration and checking observation toggles for the active profile.