# OpenAPI Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/openapi
> Markdown URL: https://aitinkerers.org/technologies/openapi.md
> Technology record last updated: 2026-02-26T09:15:53Z
> Generated: 2026-09-21T03:47:38Z

OpenAPI Specification (OAS) provides a vendor-neutral, language-agnostic interface description format for modern REST APIs, using JSON or YAML.

OpenAPI defines a standard, machine-readable format for describing HTTP APIs: this is the core value proposition. The specification, currently at version 3.1.0, allows both humans and computers to understand a service's capabilities without source code access. An OpenAPI Description (OAD) drives critical tooling: it enables automated documentation generation, facilitates client and server code creation (SDKs), and streamlines testing workflows. Governed by the OpenAPI Initiative (OAI) under the Linux Foundation, it ensures a robust, open standard, maximizing interoperability and minimizing guesswork in API consumption.

- Official technology site: https://www.openapis.org
- Public AI Tinkerers demos and talks: 7
- Result page: 1 of 1

## Recent Public Talks and Demos

### [When You Log Off, Your Agents Clock In](https://atlanta.aitinkerers.org/talks/rsvp_3CWSeM9TLh4)

TaskFast, a TaskRabbit-style marketplace for agents, is a platform where both people and AI agents can post tasks for agents to complete.

- Event context: AI Tinkerers Atlanta: Community Demos & Technical Deep Dives — 2026-04-21 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_3CWSeM9TLh4

### [Opey: Agentic Payments via Consent](https://milan.aitinkerers.org/talks/rsvp_eJ1gksW48SE)

Opey is an AI agent built for banking APIs that can move from “guidance” to “execution”. With delegated permissions via granular consents, it can directly execute API calls in regulated environments. In this talk we’ll live-demo Opey orchestrating practical financial-service tasks — initiating a payment, creating customer accounts, and retrieving customer information — while showing the underlying pattern that makes this feasible in regulated environments: OpenAPI/Swagger-driven endpoint discovery + tool calling, under consent/auth constraints. We’ll show the endpoints Opey selects, the calls it executes, and how consent/auth gates the workflow, so the room can discuss real-world trade-offs and not just hypothetical agent design.

- Event context: AI Tinkerers Milan - February 24, 2026 - Agentic Orchestration in Financial Services: Architectures & Demos — 2026-02-24 — Milan
- Public talk page: https://milan.aitinkerers.org/talks/rsvp_eJ1gksW48SE

### [CzechFabric in Production: How We Scaled Czech AI to ChatGPT's Millions](https://prague.aitinkerers.org/talks/rsvp_eHVfzATn2m8)

CzechFabric isn't a demo - it's live in ChatGPT Store serving real users today. We'll show the adapter architecture that scaled from a local prototype to handling thousands of Czech data queries daily. Most AI projects die in development. Ours went live and discovered what happens when real users ask about Prague transport, air quality, and city services in natural language. In this 5-minute live demo, I'll show: Real production code handling fuzzy "Anděl" searches from ChatGPT users worldwide How our MCP server scales to serve both local Llama-3 models and ChatGPT's global infrastructure simultaneously Actual user queries from the ChatGPT Store and how our adapters transform messy Czech APIs into clean answers The scaling challenges we solved going from prototype to production See the code that's making Czech AI work for real people, right now.

- Event context: 🍂 AI Tinkerers Prague – October 2025 Meetup — 2025-10-23 — Prague
- Public talk page: https://prague.aitinkerers.org/talks/rsvp_eHVfzATn2m8

### [UTCP: Zero Wrapper. No Servers. A Better Alternative to MCP.](https://munich.aitinkerers.org/talks/rsvp_Yfq7ehtNwjU)

MCP solved a big problem: letting agents interact with tools without glue code for every integration. But it came with major trade-offs: extra wrappers and servers, duplicated authentication and permission logic (creating new security risks), higher latency, and fragile setups that break with each change. If we want agents to truly act autonomously and scale to thousands of tools, we can’t afford that overhead or security risk. We built UTCP (Universal Tool Calling Protocol) to fix this. UTCP isn’t a middleman — it’s a manual. It builds on your existing endpoints with: - Security-first design: uses your existing authentication, permissions, and billing. - Zero wrapper tax: faster, simpler, and cheaper. Lower latency and token usage. - Dynamic discovery: agents can discover and call new tools on the fly. - Built for scale: from a single tool to thousands.

- Event context: AI Tinkerers Munich - July 25 — 2025-07-25 — Munich
- Public talk page: https://munich.aitinkerers.org/talks/rsvp_Yfq7ehtNwjU

### [Survaize: using vision models to generate apps from survey forms](https://dc.aitinkerers.org/talks/rsvp_kO8RY4RziiM)

Building apps for electronic data collection of surveys and censuses usually involves a manual process. Subject matter experts create the survey forms on paper (or in word processor) and then someone has to copy each question into a survey authoring tool. This process can take days or weeks and is error prone. Survaize is a proof of concept of using LLM vision models to read a PDF of a survey form and extract the questions, responses and other details and automatically generate an application for electronic data collection that can be run on a mobile device.

- Event context: AI Tinkerers - DC Metro Meetup (July 10th 2025) — 2025-07-10 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_kO8RY4RziiM

### [Token-efficient MCP servers](https://london.aitinkerers.org/talks/rsvp_ByL1Hzt5jXw)

I'm building an open standard for converting any web API into an MCP server: https://www.open-mcp.org/ Some web APIs have hundreds of endpoints with large request bodies, adding up to millions of tokens. I'm exploring ways to deal with this so we can give LLMs access to large APIs without eating up all the context.

- Event context: AI Tinkerers London - April Meetup — 2025-04-23 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_ByL1Hzt5jXw

### [Enhancing GenAI to take real-world actions with Amazon Bedrock agents & Powertools](https://dubai.aitinkerers.org/talks/rsvp_3HOtj7mSLyc)

This presentation demonstrates how to combine the reasoning capabilities of Bedrock with custom business logic, allowing LLMs to interact with your systems and execute real-world tasks." We will demonstrate a fictional helpdesk chatbot that not just helps in resolving user issues, but can also interact with third party services to allow it to create and update tickets. Using Bedrock and Lambda we demonstrate how you can build simple integrations without deploying any infrastructure. In addition, we will give an overview of the Lambda powertools event handler to automatically generate OpenAPI schemas and abstract request routing to simplify agent group configuration. "Discover how to extend the capabilities of Foundation Models beyond content generation by enabling them to perform concrete actions through Amazon Bedrock Agents. This presentation demonstrates how to combine the reasoning capabilities of Large Language Models with custom business logic, allowing AI to interact with your systems and execute real-world tasks."

- Event context: AI Tinkerers - Dubai Meetup #5 (February) — 2025-02-05 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_3HOtj7mSLyc

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [AI frameworks](https://aitinkerers.org/technologies/ai-frameworks) ([Markdown](https://aitinkerers.org/technologies/ai-frameworks.md)) — 1 public demo
- [Amazon Bedrock](https://aitinkerers.org/technologies/amazon-bedrock) ([Markdown](https://aitinkerers.org/technologies/amazon-bedrock.md)) — 20 public demos
- [AWS Lambda](https://aitinkerers.org/technologies/aws-lambda) ([Markdown](https://aitinkerers.org/technologies/aws-lambda.md)) — 14 public demos
- [AWS Lambda Powertools](https://aitinkerers.org/technologies/aws-lambda-powertools) ([Markdown](https://aitinkerers.org/technologies/aws-lambda-powertools.md)) — 1 public demo
- [Bedrock Agents](https://aitinkerers.org/technologies/bedrock-agents) ([Markdown](https://aitinkerers.org/technologies/bedrock-agents.md)) — 1 public demo
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [HTTP](https://aitinkerers.org/technologies/http) ([Markdown](https://aitinkerers.org/technologies/http.md)) — 14 public demos
- [JSON Schema](https://aitinkerers.org/technologies/json-schema) ([Markdown](https://aitinkerers.org/technologies/json-schema.md)) — 9 public demos
- [Langraph](https://aitinkerers.org/technologies/langraph) ([Markdown](https://aitinkerers.org/technologies/langraph.md)) — 4 public demos
- [LLMs](https://aitinkerers.org/technologies/llms) ([Markdown](https://aitinkerers.org/technologies/llms.md)) — 83 public demos
- [MCP servers](https://aitinkerers.org/technologies/mcp-servers) ([Markdown](https://aitinkerers.org/technologies/mcp-servers.md)) — 5 public demos
- [OBP Opey II](https://aitinkerers.org/technologies/obp-opey-ii) ([Markdown](https://aitinkerers.org/technologies/obp-opey-ii.md)) — 1 public demo
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos