Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Multi-agent User Interfaces
Explore multi-agent systems, framework integration, and tangible examples of user interface designs built around these multi-agent interactions.
I’ve been playing around with multi-agent systems, how they fit in to using multiple frameworks and what various pieces of UI could look like with it.
- NextNext.js is the full-stack React framework: it delivers high-performance web applications via hybrid rendering and powerful, Rust-based tooling.This is the React Framework for production: Next.js enables you to build full-stack web applications with zero configuration and maximum efficiency. It supports a hybrid rendering approach (Server-Side Rendering, Static Site Generation, and Incremental Static Regeneration) for optimal speed and SEO performance. Key features include React Server Components, Server Actions for running server code directly, and the App Router for advanced routing and nested layouts. Developed by Vercel, it leverages Rust-based tools like Turbopack and the Speedy Web Compiler for the fastest possible builds and a superior developer experience.
- CopilotKit V2CopilotKit is the open-source framework simplifying the complex last-mile of user-facing AI agent developmentCopilotKit is the open-source framework simplifying the complex last-mile of user-facing AI agent development. It provides a full-spectrum solution (headless to customized React components) for integrating AI Copilots directly into your application. The core AG-UI (Agent-User Interaction Protocol) ensures seamless interoperability: connecting any agent framework (LangGraph, CrewAI) to any client interface. Developers gain critical features like bidirectional state sharing, human-in-the-loop workflows, and real-time generative UI, streamlining the delivery of collaborative, production-ready AI experiences.
- AG-UIAG-UI (Agent-User Interaction Protocol) is the open, lightweight standard for streaming real-time, bi-directional JSON events between any AI agent backend and a user-facing frontend.AG-UI is the Agent-User Interaction Protocol: a standardized, event-based layer that solves the 'last mile' problem for AI agents. It operates over standard web transports like HTTP and Server-Sent Events (SSE), streaming a single, ordered sequence of JSON events—specifically, messages, tool calls, and state patches—to maintain perfect real-time synchronization between your agent and the UI . This open protocol eliminates the need for custom WebSocket formats or ad-hoc integrations, ensuring backend flexibility: you can swap between models like OpenAI, Ollama, or LangGraph without touching the frontend . Implementations are available via TypeScript and Python SDKs, making it the definitive contract for building reliable, production-ready agentic applications .
- Pydantic AIPydanticAI is a type-safe Python agent framework for building production LLM applications with structured data validation.PydanticAI brings the rigor of Pydantic to agentic workflows. It supports major models including GPT-4o and Claude 3.5 Sonnet through a unified interface. The framework handles structured output validation, tool calling, and dependency injection natively. By using standard Python type hints, it eliminates runtime errors in data extraction (a common pain point in AI development). It is built for engineers who prioritize reliability and clean code in their production AI stack.
- LangGraphA low-level orchestration framework for building long-running, stateful, and cyclic multi-agent systems using a graph-based architecture.LangGraph is the specialized, low-level runtime for developing complex AI agents, extending the LangChain ecosystem to handle intricate, stateful workflows. It models the agent's logic as a directed graph: nodes represent actions (LLM calls, tool use), and conditional edges dictate the flow, enabling critical features like cycles (loops) for iterative reasoning. This graph-based approach ensures durable execution, allowing agents to persist through failures and resume operations. Key capabilities include comprehensive memory management via a shared state object and built-in human-in-the-loop functionality (interrupts) for external oversight. This robust framework is trusted by production teams at companies like Klarna and Replit for deploying scalable, resilient agent architectures.
Related projects
GenZ Discord IRL Events with RSVP Emoji and Vibe Photo Checkin
Seattle
Learn how to build a Discord event system that uses emoji RSVP, AI‑evaluated attendance, and scalable LangGraph agents…
Agentic Agent Creation and Integration System
Orange County
Discover a system for integrating AI using user-friendly tools and zero-code web forms, making AI accessible for everyone…
NetShow.AI: Launching the Agent Marketplace & Agent Creation Center
Los Angeles
This talk explores NetShow.AI’s Agent Marketplace and Creation Center, demonstrating how to build, customize, and monetize intelligent agents…
Agents, Tools, Chaos: creating emergent multi-agent playgrounds!
Berlin
Building a multi‑agent simulation with GPT‑4o, Claude, and toolkits in a Phaser game, covering architecture, agent coordination, memory…
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,…
Multi-Agent Claude Code: Orchestrating Collaborative AI Coding Workflows
Seattle
Show how Claude Code’s desktop app and API orchestrate multiple agents, using @mentions for task routing and file‑based…