Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Second Brain Voice Agent API
Build a voice‑controlled Telegram bot integrating Obsidian, Garmin and macOS through a Python service, using LangChain agents and a simplified, reliable tool design.
This demo presents the architecture for a personal “knowledge processing unit” I built to act as the central nervous system for my digital life. It’s a voice-enabled Telegram bot, running on a home server, that provides an extensible API into my Obsidian vault, Garmin data, and macOS environment. The core idea is that owning your data is the first step; building a personalized agent to act on it is the next.
I’ll demonstrate how this “API” works with a live voice command and then show how its agentic design makes it easy to add new capabilities, like a specialized agent I built to find product discounts online. This is about creating a foundational platform for your own AI-powered tinkering.
Personalized Telegram AI uses Agents, ChromaDB, and AppleScript for context aggregation/automation.
Open-source Python LLM agent integrates Garmin/Obsidian for unified quantified self context grounding.
- LangChainThe open-source framework for building and deploying reliable, data-aware Large Language Model (LLM) applications.LangChain is the essential framework for engineering LLM-powered applications: it simplifies connecting models (like GPT-4 or Claude) to external data, computation, and APIs. The platform provides a modular set of components—Chains, Agents, Tools, and Memory—allowing developers to quickly build complex workflows like Retrieval-Augmented Generation (RAG) pipelines and sophisticated conversational agents. Its Python and JavaScript libraries, combined with LangChain Expression Language (LCEL), offer a standardized interface for rapid prototyping and moving applications to production with confidence.
- 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) .
- faster-whisperHigh-performance, CTranslate2-based reimplementation of OpenAI's Whisper model: up to 4x faster transcription with lower memory use.Faster-Whisper is your optimized solution for speech-to-text, leveraging CTranslate2 (a fast inference engine for Transformer models) to reimplement OpenAI's Whisper. This architecture delivers a significant performance boost: expect transcription speeds up to four times faster than the original `openai/whisper` implementation while maintaining comparable accuracy. Efficiency is key here: the model also uses less memory and supports 8-bit quantization, further improving performance on both CPU and GPU hardware. It's the go-to backend for high-speed, resource-conscious ASR (Automatic Speech Recognition) applications.
- OllamaDeploy and run open-source Large Language Models (LLMs) like Llama 3 and Mistral locally on your machine: achieve private, cost-effective AI via a simple command-line interface.Ollama is the essential tool for running LLMs locally: consider it the Docker for AI models. It packages complex models and dependencies into a single, easy-to-use application for macOS, Linux, and Windows systems. You get immediate access to models like Gemma 2 and DeepSeek-R1 via a straightforward CLI or REST API. This local-first approach guarantees data privacy and security, eliminating cloud dependency and high API costs. Ollama also optimizes performance on consumer hardware using techniques like quantization, ensuring efficient execution even on standard desktops.
- python-telegram-botA pure Python, asynchronous interface for the Telegram Bot API, utilizing the `telegram.ext` module for high-level bot development.This library delivers a pure Python, asynchronous interface for the official Telegram Bot API, compatible with Python 3.9+ environments. It goes beyond the raw API with high-level classes: specifically, the `telegram.ext` submodule provides the `Application` and various `Handler` classes (e.g., `CommandHandler`, `MessageHandler`) to streamline complex bot logic, message routing, and conversation flows. Developers use this structure to efficiently manage updates and build robust, scalable Telegram bots with minimal boilerplate code.
Related projects
Teachable AI Agents in Software Development
Poland
Learn how to build AI agents that continuously adapt to development workflows, using practical techniques and best practices…
Unleash Your voice Unleash Your Agents
Poland
The talk demonstrates a locally run AI system that provides real‑time speech transcription, lets you control applications, and…
aius.co—the long-term memory agentic framework
Poland
The session explains aius.co’s modular agentic architecture, detailing long‑term memory persistence, compute allocation, and autonomous evolution of agents…
Genaicode - programming on steroids
Poland
Live demo of Genaicode, an AI code generator, modifying a personal game in real time and covering latency,…
Voice bots revolution? Talk with your bot the old and the new way
Poland
Explore the evolution of voice bots and learn practical steps to design, implement, and integrate modern voice interfaces…
Privacy-First AI: Building Deeply Personal AI Without Data Exploitation
Poland
This talk demonstrates building agentic AI that manages personal data with explicit user control, smart prompt caching, and…