Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
ExoMind: Full Context Life AI
Learn how ExoMind uses voice AI and personal context to assess your life, set quarterly OKRs, and apply GTD for daily task management.
AI is currently quite limited in what it can do for us, and what it can do well, because it often doesn’t have the full context. We have to remind it of things we’ve already told it. But if it had the appropriate context, there are many things that we’re not good at, and the AI could take over for us, and do it better/faster/cheaper.
What if you had an AI assistant that had full context of your life goals, projects, relationships, hobbies, calendar, etc. and could help you plan your quarterly goals, weekly objectives and daily tasks. It could remind you of people in your network who can help you. It could pull down all your meeting transcripts and add those to your personal knowledgebase for later synthesis.
Experimenting with the latest Claude Skills capabilities released by Anthropic, we’ve built a tool called ExoMind that conducts a life assessment to find out your baseline, then it helps you identify your personal OKRs for the quarter, and finally it follows David Allen’s Getting Things Done (GTD) methodology to help you stay on task.
Skills can be built for anything from meal planning (taking into account your personal food preferences) to managing your WhatsApp messaging threads, and telling you what you need to pay attention to (based on what it knows you’re interested in), and who you need to get back to (based on your network of important contacts it knows about). Skills for managing your social media presence and keeping tabs on all the latest AI news.
Orchestrates 54 specialized AI agents using Claude Flow and SPARC methodology.
Claude Skills agent executes OODA tasks via MCP, observing Obsidian context.
- Claude SkillsClaude Skills packages specialized expertise—instructions, scripts, and resources—into modular, reusable components that Claude dynamically loads for complex, domain-specific tasks.Claude Skills transforms Claude into a specialist by packaging your procedural knowledge into portable, reusable folders: a `SKILL.md` file, instructions, and executable scripts. This feature (available to Pro, Max, Team, and Enterprise users) enables Claude to automatically perform complex, non-deterministic tasks like generating professional Excel spreadsheets with formulas, creating PowerPoint presentations, or processing PDFs. The system uses "progressive disclosure," loading only the skill's name and description initially, then the full content as needed, ensuring efficiency across Claude.ai, Claude Code, and the API. Developers can build custom skills for internal workflows via the Claude Developer Platform.
- Claude FlowClaude Flow is the leading AI orchestration platform for Claude Code: it deploys intelligent multi-agent swarms, achieving an 84.8% SWE-Bench solve rate.This is the enterprise-grade orchestration layer for Anthropic’s Claude Code. Claude Flow deploys specialized AI agents—up to 10 or more—in concurrent swarms, coordinating them via 'hive-mind' intelligence. This parallel execution dramatically accelerates development: expect up to a 20x speed increase over sequential AI-assisted coding. The platform integrates 87 MCP tools and a persistent memory system (SQLite) to ensure agents share context and maintain learning across sessions. Claude Flow transforms a single model into an autonomous, high-performance engineering team, proven by its 84.8% SWE-Bench solve rate.
- TypeScriptTypeScript is an open-source superset of JavaScript: it adds static typing and compiles to clean, standards-based JavaScript.TypeScript is a high-level, open-source language developed by Microsoft: it acts as a superset of JavaScript, adding a powerful static type system. This system enables compile-time type checking, catching errors before runtime (a critical benefit for large-scale applications). The TypeScript Compiler (TSC) reliably transpiles all code into clean, standards-based JavaScript (ES3 or newer), ensuring compatibility across any browser or host environment (Node.js, React.js, etc.).
- PythonPython: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
- Web scrapingDeploy automated bots to fetch, parse, and structure vast datasets (e.g., prices, reviews) from public web pages at scale.Web scraping is the automated extraction of data from websites using specialized software (bots or spiders). This process involves sending an HTTP request, receiving the HTML, and then parsing that code to isolate target data points: product prices, contact information, or news headlines. Developers frequently use Python libraries like Scrapy or Beautiful Soup to build these scrapers. The output is structured data, typically in CSV or JSON format, enabling high-value applications like competitive price monitoring across 500+ e-commerce sites or large-scale market research aggregation. We leverage this technology to turn unstructured web content into actionable business intelligence.
Related projects
The Personal AI Assistant: When Cursor Meets Claude Code for Life Management
Waterloo
Learn how to build a personal AI assistant with Cursor and Claude Code that tracks goals, automates routines,…
Building a Second Brain's API: An Extensible, Voice-Controlled Personal Agent
Poland
Build a voice‑controlled Telegram bot integrating Obsidian, Garmin and macOS through a Python service, using LangChain agents and…
Voice Assistants made easy with Amazon’s new Nova Sonic foundation model
Miami
This talk covers building real-time, bidirectional voice applications using Amazon’s Nova Sonic foundation model, with code samples and…
Yousim -- summoning identities from the latent space
New York City
This talk explores using Claude Sonnet 3.5 to simulate conversations between AI instances locating and modifying identities within…
Vital AI Agent Ecosystem + Chat.ai
New York City
Demonstration of an open standard and open-source Vital AI Agent Ecosystem for deploying agents, enabling inter-agent communication, collaboration,…
Building Real-Time Voice Agents with OpenAI's Agent SDK
Fort Wayne
Build a real‑time voice agent with LiveKit WebRTC and OpenAI’s Realtime API, using JavaScript function calls and memory…