# APIs Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/apis
> Markdown URL: https://aitinkerers.org/technologies/apis.md
> Technology record last updated: 2026-02-23T11:01:32Z
> Generated: 2026-08-26T01:26:03Z

The software intermediary: APIs (Application Programming Interfaces) define the rules for two applications to communicate, enabling secure data exchange and functionality access.

APIs are the essential contracts that allow distinct software systems to interact without exposing internal code. They operate on a request-response cycle: a client sends a structured request (often via HTTP methods like GET or POST) to a specific endpoint (URL), and the server delivers a formatted response (typically JSON or XML). Major architectural styles include REST (Representational State Transfer) and SOAP (Simple Object Access Protocol). This standardized protocol allows massive-scale integration: for example, a travel application uses the Google Maps API for location data, or a payment gateway API (like Stripe) to process a transaction securely. APIs accelerate development by leveraging existing services, drastically cutting time-to-market and development costs.

- Official technology site: https://www.redhat.com/en/topics/integration/what-is-an-api
- Public AI Tinkerers demos and talks: 19
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Pull-architecture agents: how I forced myself to do growth work](https://valencia.aitinkerers.org/talks/rsvp_-p7b50BEZW0)

A multi-agent system that manufactures pull for the growth work — writing, conference follow-up, CRM hygiene, responding to news — that I'd otherwise skip when product and ops eat my week. Seven agents across five repos, two APIs, and two websites (one fully autonomous), all driven from the only two surfaces I actually live in: my terminal and Mattermost. The demo walks a live pass through the rig: a LinkedIn contact lands in our self-hosted CRM, an article draft gets pushed to a website, a post-conference follow-up gets queued — every action is a curl command an agent emits, with circuit breakers I can tighten in the moment or across the long arc.

- Event context: AI Tinkerers Valencia May Meetup — 2026-05-26 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_-p7b50BEZW0

### [New AI visibility tool made 99% with vibe coding](https://valencia.aitinkerers.org/talks/rsvp_UStdYlRZtOI)

I built Crecerank, a tool designed to boost your brand’s visibility across the AI landscape. Crecerank is a brand monitoring platform that helps you understand the "why" behind every AI recommendation. We analyze exactly why an AI (like ChatGPT) chooses your competitor over you and identify the specific variables driving that decision. By focusing on the Latin American market and using human-behavior simulations, we deliver real, transparent data. With 64% of people now using AI to guide their buying decisions, the cost of being invisible is too high.

- Event context: AI Tinkerers Valencia April Meetup — 2026-04-21 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_UStdYlRZtOI

### [A context graph system that allows autonomous agents to make a reliable decision](https://paris.aitinkerers.org/talks/rsvp_BhRPE_2HqtA)

In this session, Yann introduces a context graph system designed to enhance how autonomous agents reason and make decisions. By structuring information as interconnected context nodes rather than isolated inputs, this approach enables agents to maintain coherence, track dependencies, and act more reliably in complex environments. The talk will explore how context graphs bridge the gap between raw data and actionable intelligence, making agent behavior more predictable, interpretable, and robust.

- Event context: AI Builders Meetup Paris - OpenClaw (featuring 42 AI & HEC Vibe) — 2026-03-26 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_BhRPE_2HqtA

### [Asset Management & AI: tech enablers, pre-requisites and examples of things that will grow](https://milan.aitinkerers.org/talks/rsvp_KVbq3zuxqvk)

In Generali Asset Management we have a series of live AI models in Asset management that are generating Alpha (investment returns) for clients and shareholders. These are advanced in terms of AI technology and advanced in terms of Asset Management usage. The talk will give a quick overview of the technology and then explore what are the pre requisites for this technology to work and then finally what I think will be coming next.

- 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_KVbq3zuxqvk

### [I built a browser that works without tabs](https://la.aitinkerers.org/talks/rsvp__xNwjDh60CI)

A browser without tabs? Yes, imagine a big canvas, like figma but the rectangles are actually chat windows, text editors, images, and regular browser windows. Everything is observed by a cognitive layer (called the "canopy") that gets all user-interactions at runtime and models the user behavior to create propositions. The founders vision on how AI-native operation systems can look like: https://disambiguate.substack.com/p/ai-wants-to-be-connective-tissue

- Event context: AI Tinkerers LA: February Builder Meetup & Live Demos — 2026-02-24 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp__xNwjDh60CI

### [Using AI to make the science behind Kabuki Syndrome more accessible](https://boston.aitinkerers.org/talks/rsvp_JYH_omkmLYc)

Kabuki Syndrome is a rare disease affecting 1 in 32,000 births. There is currently no cure, but there is a fair clip of research being conducted and published every month. As a parent of a child with Kabuki, I have long struggled to read and comprehend the dense, jargon-filled academic papers that report on this research, despite my great curiosity. Due to the rarity of the condition, there is little to no journalistic reporting on these kinds of academic papers. I will share a project I'm working on that is intended to bridge that gap with AI, using the latest LLMs to craft stories more accessible to the broader Kabuki community. In the demo I will show how I use AI to break down the papers into their individual claims, then how I transform those claims, using multiple prompts and workflows, into easy-to-read plain english versions. These plain-english versions live in a UI that has two goals. One is to be polished and reader-friendly, up to the standard of a national magazine, with subheaders, pull quotes, etc. Another is to provide an inline interactive lens onto the original text of the article, with individual sentences that can morph to show the claims and sentences in the original paper they are based on.

- Event context: {Cancelled due to Blizzard Warning } AI Tinkerers Boston: February 2026 Meetup — 2026-02-23 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_JYH_omkmLYc

### [Vibe Coding in Action: Building AI Workflows at the Speed of Thought with Anti-Gravity & Gumloop](https://tiruchirappalli.aitinkerers.org/talks/rsvp_rYaChaCn6n4)

Vibe coding is a new way of building software where intent, prompts, and flow matter more than boilerplate code. In this talk, I’ll demonstrate how developers and non-developers can rapidly create real, working AI-powered automations using Anti-Gravity and Gumloop—without writing traditional backend logic. The session will include a live demo showing how to: Design AI workflows visually Convert natural language prompts into functional pipelines Chain tools, APIs, and AI models together in minutes Iterate fast by “feeling the vibe” rather than debugging syntax The goal is to show how modern builders can go from idea → prototype → working solution incredibly fast using vibe coding principles.

- Event context: AI Tinkerers Trichy: January Meetup & Live Demos — 2026-01-31 — Tiruchirappalli
- Public talk page: https://tiruchirappalli.aitinkerers.org/talks/rsvp_rYaChaCn6n4

### [Edit AI - AI Powered Video Production Platform](https://denver-boulder.aitinkerers.org/talks/rsvp_p5Rfp5WL_Ug)

EditAI is an AI video editor that streamlines your efforts and saves time to edit & customize videos, empowering content creators and editors to replace manual workflows with smart AI-driven processes. AI-Driven Customization Automatically adds graphics, B-rolls, subtitles, transitions, soundtracks, and background music Personalizes content based on user preferences Time-Saving and User-Friendly Significantly reduces manual work Accelerates the editing process Makes video creation fast and accessible for everyone Smart Workflow Allows creators to focus on creativity rather than technical details

- Event context: Open Source & Creative AI: Using ComfyUI for Real Time Video AI — 2025-02-25 — Denver
- Public talk page: https://denver-boulder.aitinkerers.org/talks/rsvp_p5Rfp5WL_Ug

### [Agents: Thinking Fast and Slow](https://bengaluru.aitinkerers.org/talks/rsvp_PZxSQjRYFmQ)

For AI agents to operate seamlessly across diverse applications, they must dynamically expand context to retrieve relevant information and converge on the right actions without relying on predefined workflows. This talk explores how we enable agents to adapt to new environments, effectively acting as the UI for AI to navigate and interact with software systems. We'll cover: Context Expansion: Dynamically retrieving and structuring relevant knowledge for better decision-making. Convergence on Demand: Iterative reasoning strategies that refine actions through multi-step execution. Ontology-Guided Reasoning: Leveraging structured knowledge to improve accuracy and decision reliability. Real-World Applications: How these techniques allow agents to orchestrate complex workflows, break API limitations, and drive automation across SaaS tools. By combining structured retrieval with adaptive reasoning, we move beyond static integrations—unlocking AI agents that can truly think in motion and execute with precision.

- Event context: AI Tinkerers - Bengaluru - January Meetup — 2025-01-23 — Bengaluru
- Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_PZxSQjRYFmQ

### [Agentication: Turning Session Based APIs Into OAuth APIs Programatically](https://sf.aitinkerers.org/talks/rsvp_zUJvmiNVHi8)

I believe OAuth is the only solution to delegated authorization for agents that works well today. However, there is an extremely short list of services today that support OAuth. Therefore, in order to increase the secure capabilities of agents, it is important to increase the number of OAuth APIs. That's what Agentication tries to do. From the developer's perspective, they can build client applications on top of LinkedIn/X/JetBlue, for example, as if the real backend APIs were OAuth. Notes on implementation: The system consists of two main components: a central proxy server and client libraries. The proxy server acts as a secure intermediary, maintaining authenticated sessions with various services while exposing a standardized OAuth 2.0 authorization interface. Clients authenticate using a lightweight OAuth flow where they receive tokens scoped to specific hosts and permissions. When making API requests, clients include these tokens, allowing the proxy to validate their authorization before enriching the requests with the necessary session credentials. This architecture enables secure API access delegation without exposing sensitive session data, while the proxy handles all the complexity of maintaining sessions, managing cookies, and dealing with service-specific authentication requirements. The client library provides a simple interface for authorization and making proxied requests, abstracting away the underlying OAuth and HTTP mechanics.

- Event context: AI Tinkerers - San Francisco - November 2024 Meetup - Securing Agentic Systems — 2024-11-22 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_zUJvmiNVHi8

### [Pyllments - WIP - A Python package that enables a modular approach to LLM App and API creation](https://portland.aitinkerers.org/talks/rsvp_iw-iIv0Co9M)

The speed to ideation and iteration are important when building an MVP, especially when it comes to stochastic outputs where you need to swiftly see something relatively polished on your screen to pass the vibe check. Pyllments attempts to provide the building blocks necessary to create LLM apps and easily deploy their GUIs and APIs Demo is a short preview of an example RAG interface as well as dive into the philosophy and design of the package. Flow charts included.

- Event context: AI Tinkerers Portland @Nedspace - October 29th 2024, 6pm — 2024-10-30 — Portland
- Public talk page: https://portland.aitinkerers.org/talks/rsvp_iw-iIv0Co9M

### [camelAI: Talk to your tools and take action.](https://austin.aitinkerers.org/talks/rsvp_DC22FPnVwRQ)

camelAI is a Y Combinator Winter 2024 company. We link your apps to an AI chat, making complex tasks as simple as a conversation.

- Event context: Community AI Demos - September Edition — 2024-09-12 — Austin
- Public talk page: https://austin.aitinkerers.org/talks/rsvp_DC22FPnVwRQ

### [Flux, a new generation of Image Generation Models](https://boston.aitinkerers.org/talks/rsvp_UNy9T277gyY)

The Flux Generation 1 models have taken the image generation community by storm, revolutionizing AI image creation. Text to image has never been easier, and the image to image possibilities are only starting to be explored. How can someone jump into the image generation scene? This talk will cover local tools like ComfyUI and online tools like Replicate. It will also briefly cover LoRAs and what they can do for refined image generation. I don't have a project URL for this yet, but I'm planning to build image generation using Flux into my professional website because some of the APIs are so cheap.

- Event context: August 2024 Meetup at Æthos — 2024-08-26 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_UNy9T277gyY

### [Lindy – Build full-fledged AI agents in no-code](https://sf.aitinkerers.org/talks/rsvp_O6XN5nrAZrM)

We're about to release Lindy 2.0, a major rewrite of Lindy, and are demo'ing it publicly for the first time at AI tinkerers. Lindy lets you build your own AI agents in no-code in minutes — you can create extremely powerful agents talking to hundreds of APIs, conversing with users across multiple channels, keeping a human in the loop etc… in literally < 5 min.

- Event context: AI Tinkerers - San Francisco - August 2024 Meetup — 2024-08-22 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_O6XN5nrAZrM

### [BAML (Community Demo Pit)](https://seattle.aitinkerers.org/talks/rsvp_Ss-fHhJS_u8)

Stop by the community demo pit to check out amazing demos from Boundary! - BAML is an open-source tool that transforms messy prompt templates into typed functions, making AI code easier to run and test. It offers a seamless experience for developers working with various AI models, simplifying the process of building AI pipelines without hiding prompts or proxying APIs.

- Event context: AI Tinkerers Summer Social - August 2024 — 2024-08-16 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_Ss-fHhJS_u8

### [Seguridad en los LLMs (Muestra de algunas vulnerabilidades)](https://bogota.aitinkerers.org/talks/rsvp_4Rw4eXzkoNw)

Actualmente se están implementando una gran cantidad de soluciones usando diferentes LLMs por medio de API's o de interfaces de desarrollo web. Pero no se están considerando las posibles vulnerabilidades que pueden generarse con respecto a la seguridad de los datos, la integridad de la empresa y los costos de uso por token de los LLMs. Pienso mostrar en unas diapositivas, la lista de OWAST top 10 de vulnerabilidades en los LLMs y ejemplos de los mas propensos a ocurrir y que pueden afectar las aplicaciones desplegadas.

- Event context: Segundo AI Tinkerers Bogotá — 2024-06-27 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_4Rw4eXzkoNw

### [KushoAI - AI Agent for API Testing](https://bengaluru.aitinkerers.org/talks/rsvp_9mPolBV8Ja8)

Kusho helps you reclaim engineering team bandwidth and ship fast without worrying about unnoticed bugs. Kusho's fine-tuned models are trained to understand API context, write and execute comprehensive tests, and provide analyzed results for debugging, all in sync with your CI/CD process. With Kusho, you get an auto-updating testing set up across hundreds of APIs in hours.

- Event context: AI Tinkerers - Bangalore Inaugural - RSVP REQUIRED — 2024-06-02 — Bengaluru
- Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_9mPolBV8Ja8

### [Storia Lab](https://nyc.aitinkerers.org/talks/rsvp_v2DaAK0pn_c)

Storia AI is building contextual intelligence for storytelling. After launching our storyboarding tool for filmmakers, we learnt about their ardent need for control over AI-generated imagery. We are now actively working on a slew of very specialized image post-processing APIs that can bring control back into human hands. Our first model, Textify, has the ability to seamlessly replace AI-generated gibberish with your desired text. There are a lot more APIs to come, and, if you're in the business of image generation, we're excited to hear more about your controllability needs.

- Event context: AI Tinkerers NYC - October Meetup — 2023-10-26 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_v2DaAK0pn_c

### [BookNote](https://sf.aitinkerers.org/talks/rsvp_fytFeb3PERc)

-- Summary -- BookNote is a new computing abstraction for end-user programming - allowing anyone to quickly build & deploy micro-tools and long-tail software to get things done. This includes stuff like python scripts for data wrangling, cleaning & visualization. Chaining a bunch of different APIs together to get stuff done. Being able to quickly build frontends for the above tasks. BookNote does this by taking the free-form NL to Code abilities of LLMs and makes it visual, auditable & shareable. BookNote generates both JS frontends and python backends. The super cool part is that the python code runs in the browser (via pyodide) right away AND the js frontend is able to talk to the python backend. So, the tools/apps are ready to go with no deployment time/effort. The JS frontend generation also make the whole process a lot more visual, fun & auditable! For the talk, we'd love to demo our prototype and also give attendees a look into how it works under the hood :) -- Sample BookNotes -- These are very much hacky WIP prototypes so pardon us if they bug out :) Gallery https://www.booknote.cloud/editor/265z8pof5w6 Chaining Multiple APIs https://www.booknote.cloud/editor/oykst6b9pw Chuck Norris Joke Generator https://www.booknote.cloud/editor/djfy7a3kvia Data Enrichment + Plotting https://www.booknote.cloud/editor/dbr9kvrlicg Data Cleaning + Plotting https://www.booknote.cloud/editor/85sx8iq4fal Interactive Plots https://www.booknote.cloud/editor/1ondtnicclc

- Event context: 🤖🔄🧠 AI Tinkerers SF - August Meetup — 2023-08-10 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_fytFeb3PERc

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 654 public demos
- [LLMs](https://aitinkerers.org/technologies/llms) ([Markdown](https://aitinkerers.org/technologies/llms.md)) — 83 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 96 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 102 public demos
- [AI agents](https://aitinkerers.org/technologies/ai-agents) ([Markdown](https://aitinkerers.org/technologies/ai-agents.md)) — 35 public demos
- [No-code](https://aitinkerers.org/technologies/no-code) ([Markdown](https://aitinkerers.org/technologies/no-code.md)) — 2 public demos
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 111 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 216 public demos
- [Agent](https://aitinkerers.org/technologies/agent) ([Markdown](https://aitinkerers.org/technologies/agent.md)) — 12 public demos
- [AI agent](https://aitinkerers.org/technologies/ai-agent) ([Markdown](https://aitinkerers.org/technologies/ai-agent.md)) — 8 public demos
- [AI models](https://aitinkerers.org/technologies/ai-models) ([Markdown](https://aitinkerers.org/technologies/ai-models.md)) — 6 public demos
- [AI pipelines](https://aitinkerers.org/technologies/ai-pipelines) ([Markdown](https://aitinkerers.org/technologies/ai-pipelines.md)) — 1 public demo
- [Anti-Gravity](https://aitinkerers.org/technologies/anti-gravity) ([Markdown](https://aitinkerers.org/technologies/anti-gravity.md)) — 1 public demo
- [API Testing](https://aitinkerers.org/technologies/api-testing) ([Markdown](https://aitinkerers.org/technologies/api-testing.md)) — 3 public demos
- [Astro (personal/autonomous site work)](https://aitinkerers.org/technologies/astro-personal-autonomous-site-work) ([Markdown](https://aitinkerers.org/technologies/astro-personal-autonomous-site-work.md)) — 1 public demo
- [BAML](https://aitinkerers.org/technologies/baml) ([Markdown](https://aitinkerers.org/technologies/baml.md)) — 11 public demos
- [Browser](https://aitinkerers.org/technologies/browser) ([Markdown](https://aitinkerers.org/technologies/browser.md)) — 5 public demos
- [camelAI](https://aitinkerers.org/technologies/camelai) ([Markdown](https://aitinkerers.org/technologies/camelai.md)) — 1 public demo