Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Agentify converts agents to Agentuity
Learn how Agentify converts existing open‑source AI agents into runnable Agentuity projects by parsing documentation, extracting TypeScript, structuring files, and generating pull requests.
The Agentify Agent is an agent built on Agentuity that takes links to open-source AI agent examples (like CrewAI or Mastra) and automatically converts them into runnable Agentuity agents. It analyzes docs, extracts runnable TypeScript snippets, sets up the correct folder structure, and opens a pull request with a ready-to-run example. I’ll walk through how the agent interacts with Devin (the AI software engineer), how the prompt architecture was designed, and what we learned about agent onboarding.
- Agentuity SDKThe full-stack platform for building, deploying, and managing production-ready AI agents with end-to-end type safety.The Agentuity SDK is your comprehensive toolkit for developing, deploying, and operating AI agents, primarily targeting Node.js and Bun environments. This platform handles the full stack: you get built-in APIs, React frontends, and native access to tools like Redis, Postgres, and vector storage. The SDK enforces end-to-end type safety via input/output schemas, ensuring robust code and runtime validation. It’s framework-agnostic, wrapping existing agent code from tools like the Vercel AI SDK or LangGraph, and provides deep observability with OpenTelemetry tracing and automatic I/O integrations for email, SMS, and webhooks. Ship complex, multi-agent workflows with minimal infrastructure overhead.
- 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.).
- BunBun is the fast, all-in-one JavaScript runtime and toolkit: it replaces Node.js, npm, and multiple development tools with a single, cohesive executable.Bun delivers a high-performance JavaScript runtime, built from scratch in Zig and powered by Apple's JavaScriptCore engine (not V8). It functions as a drop-in replacement for Node.js, but unifies the entire development workflow: the runtime, package manager (e.g., `bun install`), bundler (`bun build`), and test runner (`bun test`) are all integrated. This architecture dramatically reduces startup times and memory usage, offering significant speed gains, especially in tasks like package installation (up to 30x faster than npm) and server-side rendering.
- Devin APIThe Devin API programmatically integrates the autonomous AI software engineer, enabling end-to-end code generation and complex engineering task automation.The Devin API connects your applications directly to the AI software engineer, Devin, for full workflow automation. It provides multiple versions (e.g., v3beta1) for programmatic session creation and management, supporting use cases like automatic PR reviews, lint error resolution, and data migrations. Devin autonomously writes, runs, and tests code: it refactors code, handles bugs, reviews pull requests, and builds internal tools, effectively crushing your backlog. This is a direct integration for serious engineering teams looking to delegate complex, multi-step development tasks.
- GitHub ActionsGitHub Actions automates your software workflows (CI/CD, testing, deployment) directly within your repository.GitHub Actions is your native, event-driven automation platform: it executes custom workflows right inside your GitHub repository. Define multi-step jobs using YAML files, which must be stored in the `.github/workflows` directory. These workflows trigger on specific events, like a `push` to a branch or a `pull_request` opening. The platform supports world-class Continuous Integration and Continuous Deployment (CI/CD), letting you build, test, and deploy code across any language (e.g., Python, Node.js, Java). Runners—Linux, Windows, or macOS virtual machines—execute the jobs. For security, confidential data is managed via GitHub `secrets`, ensuring credentials stay out of your code.
Related projects
Build Your Own AI Agent with ADK
Miami
Hands‑on workshop shows how to use Python and the Agent Development Kit to build, integrate data and tools,…
agents as contracts - everyone hates reading
Miami
Explore how autonomous agents can automate contract creation, execution, and monitoring, showing real‑world implementations and the practical challenges…
Give your agent personality
Miami
Learn how to create agent personas reflecting user types, workflows, and decision patterns, expanding on existing agency-agent concepts…
Your AI Agent Just Designed Its Own Face (And Changed My Dashboard Without Asking)
Miami
See how an AI agent designed its own face using Gemini, saved it, and updated its dashboard avatar…
Creating AI Agents in JavaScript
Miami
Live demonstration of building a JavaScript multi‑agent system using KaibanJS, showing role‑based agents, shared memory, LLM integration, tool…
AI agents as interface layer for mobile apps
Tiruchirappalli
Explore AI agents as the primary mobile interface, bypassing traditional UI. See a live demo showing intent directly…