Honcho Integration

Wires Honcho's memory and social cognition library into your Python or TypeScript codebase. Honcho builds rich representations of participants over time by reasoning about conversation history, so your AI can query "What does this user care about?" or "How technical is this person?" and get grounded answers. The skill walks through exploration, asks pointed questions about which entities to track (users, AI agents, both), how sessions map to your app's conversation structure, and whether you want tool-based queries or pre-fetched context. Then it handles SDK setup, peer creation, and message storage. Includes specific guidance for bot frameworks like nanobot and openclaw. Works with any model or framework since it's just async reasoning in the background.

skills.sh installs: 903
GitHub stars: 8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add plastic-labs/honcho --skill honcho-integration --agent claude-code

Installs into .claude/skills of the current project.

Files

Honcho Integration Guide

What is Honcho

Honcho is an open source memory library for building stateful agents. It works with any model, framework, or architecture. You send Honcho the messages from your conversations, and custom reasoning models process them in the background — extracting premises, drawing conclusions, and building rich representations of each participant over time. Your agent can then query those representations on-demand ("What does this user care about?", "How technical is this person?") and get grounded, reasoned answers.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly