Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
OpenClaw: Long-term AI Memory
Explore Openclaw's memory, discuss AI agent memory needs, and learn how Honcho enhances Openclaw with easy customization for better long-term memory.
Walk through of the Openclaw + Honcho Demo.
Discussion about the memory behavior in OpenClaw.
Discussion of what makes better memory for AI Agents.
TypeScript plugin providing Honcho's dialectic reasoning and peer-modeling for OpenClaw.
Honcho provides AI-native memory via a dual-peer model and CLI.
- OpenClawOpenClaw is the viral, open-source, autonomous AI agent: a self-hosted 'digital employee' that executes real-world tasks across your local machine and messaging platforms 24/7.This is the next-generation autonomous AI agent, built by Peter Steinberger (founder of PSPDFKit). OpenClaw functions as a proactive, self-hosted assistant, running as a long-running Node.js service on your own hardware (e.g., a Mac Mini or VPS) for about $3–$5 per month. It integrates directly with chat apps (WhatsApp, Telegram, Discord) to receive instructions and report completions. The agent utilizes over 100 AgentSkills to execute complex, real-world workflows: clearing your inbox, writing code, managing documents, and checking you in for flights. The open-source project’s velocity is undeniable, having surpassed 100,000 GitHub stars quickly and reportedly driving a surge in Mac Mini sales.
- HonchoHoncho delivers AI-native memory: a state-of-the-art library providing perfect recall and superhuman social cognition for your next-gen AI agents.This is the core engine for agent intelligence. Honcho is an AI-native memory library engineered for developers building complex AI systems. It provides agents with perfect, long-term recall and sophisticated user/agent modeling, enabling hyper-personalized experiences and complex social cognition across multi-agent systems. The platform maps personal identity to engineer optimal context on demand, utilizing a Dialectic API for natural language queries against stored history. Integrate it via a simple `$ pip install honcho-ai` to ensure your agents understand who they are, who they are interacting with, and what happened, without you managing the context manually.
Related projects
OpenClaw Trace - Recursively Self-improving OpenClaw
New York City
This talk showcases a system for recursively improving OpenClaw by identifying and fixing real-world user issues. It uses…
Securing OpenClaw for fun and profit
New York City
Learn how to secure AI infrastructure by exploring the development of z0, an OpenClaw host, and its integrated…
wayyOS ~ agentic swarm management in a desktop environment
New York City
Explore wayyOS, an agentic swarm for desktop environments. Discover its architecture, global context management, and inter-AI synchronicity, reimagining…
ROSClaw: Agentic Robots with OpenClaw - "what happens when you give a robot a lobster brain?"
New York City
See ROSClaw, a framework integrating OpenClaw with ROS2 and ESP32 devices. Explore installation, running ROS2 packages, and observe…
Self-Improving Agents with Honcho
New York City
Learn to build stateful, self-improving agents. Honcho provides a memory agent to prevent context rot, enabling your OpenClaw…
Collaborator: Lobster-powered critical thinkig partner
New York City
Discover open-source tools that transform an OpenClaw agent into a thinking partner. Explore Seedvault for knowledge syncing, Reflection…