honcho

Configure Honcho APIs for cross-session memory and per-profile AI peers.

Updated Apr 20, 2026
One-click install
npx skills add https://github.com/matthew-johnson/hermes-agent --skill honcho-matthew-johnson
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: honcho
Source: https://github.com/matthew-johnson/hermes-agent/tree/main/optional-skills/autonomous-ai-agents/honcho
Command: npx skills add https://github.com/matthew-johnson/hermes-agent --skill honcho-matthew-johnson

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Honcho provides AI-native cross-session user modeling by storing and federating memory across Hermes profiles while keeping each profile's AI peer distinct. It also enables per-profile observation controls, session summaries, and memory governance to improve recall and dialectic quality without data leakage between profiles.

Core Features & Use Cases

  • Cross-session memory: shared user representation with per-profile AI peers and isolated observations.
  • Memory governance: observe controls, per-profile recall modes, and session summaries to maintain context budget and privacy.
  • Flexible deployment: cloud or self-hosted Honcho setups with profile synchronization and memory tooling support.

Quick Start

Install and configure Honcho for Hermes, then enable memory for a profile and verify status

Frequently Asked Questions about honcho

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

FAQPage Schema
How do I add cross-session memory to my AI application?

Cross-session memory stores and federates user context across profiles using Honcho APIs, enabling consistent recall without data leakage. It isolates observations per profile so each AI peer maintains distinct context.

What's the best way to isolate memory between different user profiles?

Per-profile host blocks isolate memory by assigning distinct AI peers and observation controls to each profile. This prevents data leakage while allowing shared user representation across sessions.

Can I self-host Honcho for cross-session memory management?

Yes, Honcho supports both cloud and self-hosted deployments. You can configure profile synchronization and memory tooling through Honcho APIs regardless of your chosen deployment setup.

How does cross-session memory governance handle privacy and context budgets?

Memory governance uses observation controls, per-profile recall modes, and session summaries to maintain privacy and optimize context budgets. These features ensure recall quality without exceeding data boundaries.

What memory tools are available for profiling and searching user context?

Available memory tools include profiling, searching, and reasoning capabilities. These tools help manage cross-session user modeling by storing, federating, and retrieving context across Hermes profiles.

Why does my AI peer lose context across different sessions?

AI peers lose context without cross-session memory because sessions operate independently. Honcho solves this by federating memory across profiles, applying session summaries and recall modes for consistent user modeling.