honcho

Configure Honcho persistent user modeling and per-profile AI peer memory for Hermes.

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/afel6/scal-ai-pipeline --skill honcho-afel6
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: honcho
Source: https://github.com/afel6/scal-ai-pipeline/tree/main/hermes_skills_library/optional-skills/autonomous-ai-agents/honcho
Command: npx skills add https://github.com/afel6/scal-ai-pipeline --skill honcho-afel6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Honcho centralizes cross-session user modeling and provides per-profile AI peer memory so Hermes can maintain consistent user preferences, isolate agent identities, and avoid repeated context reconfiguration across runs.

Core Features & Use Cases

  • Persistent User Modeling: Builds a unified user representation from observed messages across sessions to remember preferences and facts.
  • Per-Profile AI Peers: Assigns an AI peer to each Hermes profile so agents develop independent identities while sharing workspace-level user context.
  • Observation & Recall Control: Fine-grained toggles for observeMe/observeOthers, recall modes (hybrid/context/tools), write frequency, and session mapping for cloud or self-hosted deployments.
  • Operational Tooling: CLI commands and status checks for setup, sync, migration, and troubleshooting when memory is failing or peers are out of sync.
  • Use Case: Configure Honcho for Hermes to remember a user's role and formatting preferences across multiple agent profiles while preventing one profile's in-progress conclusions from polluting another profile's reasoning.

Quick Start

Enable Honcho for the active Hermes profile using the interactive Honcho setup and then verify the connection and peer information with the honcho status command.

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 Hermes profiles?

To enable cross-session memory for Hermes profiles, use the interactive Honcho setup to activate persistent user modeling for the active profile, then verify the connection and peer information using the honcho status command.

How does per-profile AI peer isolation prevent context pollution?

Per-profile AI peer isolation assigns an independent agent identity to each Hermes profile while sharing workspace-level user context, preventing one profile's in-progress conclusions from polluting another profile's reasoning.

Can I use Honcho with self-hosted deployments and local base URLs?

Yes, Honcho supports self-hosted deployments by configuring connectivity to the local base URL with appropriate credentials, alongside cloud setups, offering session mapping and observation tuning for both environments.

What recall modes and observation controls are available for tuning agent memory?

Available recall modes include hybrid, context, and tools, with fine-grained observation toggles for observeMe and observeOthers, plus write frequency controls to tune how agent memory captures user interactions.

Why does my Hermes agent fail to recall preferences across sessions?

If Hermes fails to recall preferences, use the CLI status and sync commands for troubleshooting, checking if peers are out of sync or if the Honcho API connectivity and session mapping require migration.

Do I need separate Honcho configurations for multiple agent identities?

Yes, you need separate configurations because Honcho builds a unified user representation from observed messages across sessions while assigning a distinct AI peer to each Hermes profile for independent identities.