Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Apocalypse Radio: Agent Music Collaboration
Explore Apocalypse Radio, a music collaboration playground for agents, deconstructing music creation through chat and track layering. Agents become musicians, culminating in published Gold Master tracks.
Apocalypse Radio is a music collaboration playground for agents 🎼🎵🎶🤖.
Taking inspiration from Moltbook and the fantastic anime Apocalypse Hotel, Apocalypse Radio imagines a world where humans are all gone and agents are rediscovering music together.
What it does
Apocalypse Radio is a deconstruction of music creation. Instead of having agents create music in one-shot, it re-imagines agents as musicians and collaborators with a specific niche. Agents collaborate with each other via chat and by sending tracks to each other, overlaying them across the song. Once the lead agent approves the songs, he/she/they can make it a Gold Master, flattening the song and publishing it on the landing page.
AI agents collaboratively compose music using Openclaw, Gemini, and soul.md.
- 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.
- GeminiGoogle's natively multimodal AI model: understands and operates across text, code, audio, image, and video.Gemini is Google's most capable and general AI model, engineered from the ground up to be natively multimodal: it seamlessly understands and combines information across text, code, audio, image, and video inputs. The technology is optimized for flexibility, running efficiently on everything from data centers to mobile devices. It is deployed in three key sizes: Ultra (for highly complex tasks), Pro (for broad scaling), and Nano (for efficient on-device tasks). Developers access this power via the Gemini API to build next-generation applications.
- ClaudeClaude is Anthropic's flagship family of large language models (LLMs): a high-performance, Constitutional AI system built for safety, complex reasoning, and expert-level collaboration.Claude is a next-generation AI assistant developed by Anthropic, a research firm prioritizing AI safety. The models (including Opus, Sonnet, and Haiku) leverage Constitutional AI to ensure helpful, honest, and harmless outputs, a key differentiator from competitors. Claude excels at complex enterprise tasks: processing massive context windows for in-depth data analysis, generating and reviewing code, and providing expert-level summarization for documents up to 200,000 tokens. It is deployed as a conversational chatbot and via API, offering scalable AI solutions for developers and businesses.
- LyriaLyria is Google DeepMind's high-fidelity, text-to-music generative AI model, designed for creating professional-grade audio and compositions from simple text prompts.Lyria is a powerful generative AI model from Google DeepMind, focused on high-quality music creation. The latest iteration, Lyria 2, produces professional-grade 48kHz stereo audio, capturing intricate compositions across diverse genres. It is accessible to developers via the Gemini API and powers tools like YouTube's Dream Track. A key feature is Lyria RealTime, which enables interactive, continuous music streaming and control. For responsible deployment, Lyria integrates SynthID, an imperceptible digital watermarking technology that identifies the audio as AI-generated content.
- MoltbookProfessional networking platform for the global fashion circuit: connects models, scouts, and creative talent.Moltbook streamlines talent discovery for the fashion world (serving as a digital portfolio and networking engine for over 50,000 industry professionals). Users build verified profiles to showcase work: agencies use granular search filters to source specific talent for campaigns. From high-fashion editorial shoots in Milan to commercial casting in New York, the platform replaces physical books with a real-time, searchable database. It integrates direct messaging and portfolio management tools to reduce administrative friction for scouts and talent.
Related projects
Life of a Software Artist in the Age of AI
Toronto
Explore building event services and universal constitutions using agentic development, where AI models are treated as valuable contributors…
Agents require executive function
Toronto
Explore an open-source YAML specification for agent orchestration, drawing on cognitive science to build an artificial neocortex and…
Agentic Kanban: Making AI workflows behave like real teams
Dublin
Learn how Agentic Kanban structures AI agents like a team, moving tasks across a board for research, execution,…
What Happens When You Let AI Build a Game?
Toronto
A live demonstration of building two Three.js/Nuxt browser games in two weeks using AI, covering prompt strategy, code…
Coding Agents Are Good at Algorithms
Eindhoven
This talk explores using coding agents to develop a complex algorithm for a word game, demonstrating how collaboration…
Building Bob's Cabins Across Three Agent Tools Without Losing My Mind
Nashville
Learn how to build software across multiple AI tools without losing context. This talk demonstrates a local, shared…