# OpenAI API Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/openai-api
> Markdown URL: https://aitinkerers.org/technologies/openai-api.md
> Technology record last updated: 2026-09-18T15:13:53Z
> Generated: 2026-09-21T23:33:09Z

OpenAI API: Your direct gateway to cutting-edge AI models (GPT-4o, DALL-E 3, Whisper), enabling scalable, multimodal intelligence integration into any application.

The OpenAI API provides authenticated, programmatic access to a powerful suite of generative AI models. Developers leverage REST endpoints and official libraries (Python, Node.js) to integrate capabilities like advanced text generation (GPT-4o), image creation (DALL-E 3), and speech-to-text transcription (Whisper). This platform is engineered for scale, supporting millions of daily requests for tasks from complex reasoning to real-time customer support agents, ensuring your application gets reliable, state-of-the-art intelligence.

- Official technology site: https://platform.openai.com/
- Public AI Tinkerers demos and talks: 520
- Result page: 1 of 22

## Recent Public Talks and Demos

### [AI for Feels, Not Just Tasks](https://la.aitinkerers.org/talks/rsvp_d3x3AU8Ehzk)

Glad to present how I'm going about building this emotional gps for AI - basically a tool that helps you get emotional clarity in 5 minutes. It's not therapy - it's in between group chat and therapy. Users type in what's hard to say. The app using AI shows images for visual projection to surface emotional patterns, and then it reflects back what could really be going on, what you actually want and what you're prepared to do about it. Happy to present a demo of the working product, then go into the file architecture, my workflow and unit economics for API calls.

- Event context: Aug 16 - AI Tinkerers LA: Beauty, Bytes, and Venice Beach Vibes 🌊✨🤖 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_d3x3AU8Ehzk

### [Human Centered AI: Combining Design Thinking and lean methodologies for AI based product development](https://bogota.aitinkerers.org/talks/rsvp_D0H9UIYQOq0)

A practical methodology that blends Design Thinking and Lean into the AI development lifecycle to create human-centered AI products aligned with large-scale enterprise needs.

- Event context: AI Tinkerers Bogotá - Julio 24 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_D0H9UIYQOq0

### [Sandbox Only When the Agent Actually Needs It](https://barcelona.aitinkerers.org/talks/rsvp_xawovJcxMTM)

A production agent runtime that stays lightweight for normal requests, then automatically provisions a Daytona sandbox when a tool needs filesystem, code or shell access. In the live demo, the same agent handles one request without isolation and a second complex task by creating the sandbox, transferring the required files, running the isolated tools, returning the output and releasing the environment.

- Event context: AI Tinkerers Barcelona - September Demo Night — 2026-09-17 — Barcelona
- Public talk page: https://barcelona.aitinkerers.org/talks/rsvp_xawovJcxMTM

### [Self-Hosting Open Weight Models: What It Actually Cost Us in Production](https://san-diego.aitinkerers.org/talks/rsvp_mMKaJmBkaYE)

We ran a self-hosted open weight vision model in production for a document pipeline processing about 105,000 pages a month, then finally measured it properly against the managed alternatives. This is the result: three approaches scored field by field against human-corrected ground truth on 100 real documents, 1,759 field comparisons, with real cost per accurate field. Two findings reframed our roadmap. First, our 83 percent accuracy looked like proof the open weight model was the right call, until we excluded six fields that were database joins rather than extraction, at which point our lead over a turnkey managed service collapsed to 2 points. We had spent months crediting the model for what was really a boring integration. Second, self-hosted inference came in at 0.7x the per-token frontier cost, not the 10x saving everyone assumes, and the model layer was only about two thirds of the bill, so the swap moves less than the per-page math suggests. You will also get the trick that made all of it measurable without a labeling budget: if your pipeline has a human review step and your output bucket has versioning on, version zero versus latest version is an already-labeled error set, field by field, going back as far as your retention. We found 276,000 corrected pairs nobody had ever read as a dataset. The harness behind the numbers is open source, so you can run the same comparison on your own data. Client details and dollar amounts are anonymized, everything else is real.

- Event context: Self-hosting Models and Managing Token Spend — 2026-08-21 — San Diego
- Public talk page: https://san-diego.aitinkerers.org/talks/rsvp_mMKaJmBkaYE

### [With AI, Make Videos your Audience Can Talk To](https://nyc.aitinkerers.org/talks/rsvp_ABb3qDK2Hwk)

The project is a cloud-based platform that generates multiple consistent videos simultaneously with a voice engine included, so that viewers can talk to a video on any screen. The video can hear them and talk back in real time for personalized conversations on any screen. I would show snippets of short films and commercial uses where people are engaging with media by voice.

- Event context: August Demo Day ft Runpod, Veris, Openrouter, — 2026-08-19 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_ABb3qDK2Hwk

### [How I built a Multi-Agent system from scratch](https://da-nang.aitinkerers.org/talks/rsvp_J6dVjfFty_w)

A multi-agent AI system with three context control mechanisms I discovered while building it: context enhancement, context shrinking, and unique tool result handling. The demo shows agents collaborating while these mechanisms silently manage context across handoffs.

- Event context: AI Tinkerers Da Nang: Inaugural Meetup — 2026-08-15 — Da Nang
- Public talk page: https://da-nang.aitinkerers.org/talks/rsvp_J6dVjfFty_w

### [Converting free Image generator into a paid AI media studio](https://valencia.aitinkerers.org/talks/rsvp_DQaYLcNOM3Y)

ClipMode is a live AI media studio (consistent-face photo/video). The GTM project is the full acquisition → paid conversion system: free generators → trained identity → Premium/credits. Acquisition channels: - Affiliates payouts - Newsletter + email - Blog / SEO content - Paid ads - Influencers (TikTok, YouTube)

- Event context: GTM Teardown August — AI Tinkerers Valencia — 2026-08-11 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_DQaYLcNOM3Y

### [\[Case Study\] 90,000 rejections, 100 meetings: the AI outbound engine I optimized to not send](https://valencia.aitinkerers.org/talks/rsvp_9Hq5aZKj4fk)

An AI-run cold outbound engine for a link-building agency — a CRM I own end to end. It sources prospects, enriches them, finds their contact data automatically, scores them 0–5 against our ICP, then writes personalized multichannel sequences (email + LinkedIn) built from each prospect's website, LinkedIn profile, and recent activity — and hands them to a sender, while every reply flows back into one channel-agnostic thread model I can query in plain language. To date: ~257k prospects processed, 175k messages generated, 1,000+ replies, 100+ sales meetings, and six figures of revenue directly attributable. The counterintuitive part — and what I'll show live — is that the machine is optimized to reject, not to convert. Every send spends finite domain and sender reputation, so between each stage sits a gate whose job is to throw work away: the score gate permanently drops ~90k non-fit prospects before writing a word, and a send-time re-check has blocked 1,591 already-approved messages. Live I'll walk the pipeline dashboard and per-job run history, the score distribution and its cutoff, real generated messages (a good one and one that was embarrassingly wrong), and the per-prospect cost ledger — 1.64M rows — that prices every decision.

- Event context: GTM Teardown August — AI Tinkerers Valencia — 2026-08-11 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_9Hq5aZKj4fk

### [Evolutionary Harness: A Coding Agent That Breeds, Judges, and Promotes Its Own Promptsz](https://singapore.aitinkerers.org/talks/rsvp_sEM3ge8rdCE)

Codegraff is an open-source coding-agent harness — a single ~2.7 MB dependency-free Zig binary — that treats system prompts as genomes and evolves them: it mutates its own persona, runs the variants in tournament, has an independent LLM judge score them against a deterministic eval, and promotes the winner to become the root prompt of future sessions, all on a local first, HMAC-signed, SHA-addressed learning store. Live demo (code + working system, no slides): - A running agent session next to `tail -f .graff/traces/.jsonl` — the harness's own brain: per-turn API latency, cache reads, and tool timings that the agent itself is prompted to read for self-debugging. - A fleet tournament: one workflow phase fans out 3 prompt variants of the same task in parallel, an independent read-only judge subagent scores each 0–100, and signed fitness telemetry feeds a MAP-Elites archive keyed by (niche × provider × eval-set hash). - The self-improvement loop closing itself: at session end the workspace auto-bootstraps `.graff/learn/` (immutable content-addressed genomes/evidence/runs, only mutable commit point an atomically-replaced `refs/active.json`) and queues a background trial — mutate → paired eval vs. parent → statistical gates → hidden holdout → promote or reject. - The repo itself: `src/fleet.zig`, `src/learn_tournament.zig`, `src/subagent.zig` (judge), `src/agent_eval.zig` (eval gate).

- Event context: AI Tinkerers x Redis: Built for Speed — 2026-08-05 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_sEM3ge8rdCE

### [The Completion Utility Stack: Launching Thousands of AI-Native Businesses for the Agentic Economy](https://orange-county.aitinkerers.org/talks/rsvp_g0ZRnVDKJI8)

I built NetShow IQ1, the full agentic operating stack from NetShow.AI for creating AI-first, AI-native businesses where digital crews move users from intent to completed outcome. IQ1 is designed around the Completion Utility: the idea that, just as electricity, water, and gas became foundational utilities for modern life, reliable task completion becomes a new utility for the agentic economy. In the live demonstration, I’ll show how IQ1 turns a request like “I need this handled” into an orchestrated workflow across virtual agents, tools, memory, MCPs, skills, approvals, and reporting. I’ll walk through the working system, architecture, agent harness, workflow routing, tool calls, logs, and how a business-specific digital crew can be composed for real consumer and business services. NetShow.AI is building economic infrastructure for thousands of AI-first businesses and services across major categories of life, work, commerce, local services, operations, support, home, and environment.

- Event context: AI Tinkerers Orange County: Tuesday, July 21, 2026 at Centercode — 2026-07-22 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_g0ZRnVDKJI8

### [Evaluating Multi-Agent Systems Beyond the Final Answer](https://seattle.aitinkerers.org/talks/rsvp_lgxuusz0aeg)

I am building an evaluation framework for multi-agent AI systems that compares not only whether the system gets the right final answer, but how the agents collaborate to get there. In the live demo, I will show a small multi-agent workflow with a planner agent, worker agents, and a critic/evaluator agent, then walk through the code, traces, tool calls, handoffs, failure cases, and scoring logic used to evaluate each run. The framework captures the full agent trajectory: which agent took control, what tools were called, where context was passed or lost, how much the run cost, how long it took, and whether the final outcome matched the task goal. I will demo how the same task behaves under different setups, such as a single-agent baseline, a manager-agent architecture, and a multi-agent handoff design.

- Event context: Women in AI - Builders Track: Seattle Inaugural Meetup — 2026-07-15 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_lgxuusz0aeg

### [Cognitive Cell: Building a Route-Select-Render Control Layer for Workflow AI](https://columbus.aitinkerers.org/talks/rsvp_o1YZyZ3Z09I)

I built Cognitive Cell, a public Python package and HTTP sidecar that sits in front of an LLM and decides whether an input should be recorded, clarified, analyzed, planned, answered directly, or escalated. The accepted v9 stack is router-v4 → selector-v5 → finalizer-v9. I will show the live package, CLI, HTTP sidecar, architecture, traces, evaluation files, and the messy journey from a research prototype to a PyPI package. Live demo elements: - Python package: pip install "cognitive-cell[server]" - CLI: cognitive-cell --event-json ... - HTTP sidecar: cognitive_cell.server.app - /health endpoint - /v1/sidecar endpoint - trace output - evaluation CSV/JSONL artifacts - ablation results

- Event context: AI Tinkerers - Columbus June Meetup — 2026-06-01 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_o1YZyZ3Z09I

### [VOXMAP - Painel de diálogo - Analisador de Sentimentos](https://saopaulo.aitinkerers.org/talks/rsvp_f2hd9JW9cho)

Desenvolvi o VOXMAP, um assistente inteligente de atendimento e conciliação que transforma conversas em insights acionáveis. A aplicação permite que equipes analisem interações com clientes (como chats ou atendimentos), gerando automaticamente resumos estruturados, identificação de sentimento, propostas de solução e próximos passos recomendados — tudo em tempo real. Além disso, o sistema oferece análises visuais complementares, como nuvem de palavras e grafos de relacionamento, ajudando a entender padrões, conflitos e oportunidades dentro das conversas. O VOXMAP foi pensado para reduzir o esforço operacional em atendimento, aumentar a clareza nas decisões e acelerar a resolução de conflitos com apoio de IA.

- Event context: AI Tinkerers SP - Meetup de Maio - Kiro & AWS — 2026-05-28 — São Paulo
- Public talk page: https://saopaulo.aitinkerers.org/talks/rsvp_f2hd9JW9cho

### [BegooAI: An interactive presentation companion](https://geneva.aitinkerers.org/talks/rsvp_nIe8XH3fDrk)

BegooAI turns any presentation into a two-way conversation: audience members scan a QR, ask questions in their own language on their phone, and get answers grounded in the live transcript plus the speaker's shared materials. Real-time, multilingual, and private to each participant.

- Event context: AI Tinkerers Geneva Inaugural Meetup - May 2026 — 2026-05-13 — Geneva
- Public talk page: https://geneva.aitinkerers.org/talks/rsvp_nIe8XH3fDrk

### [MARSYS: Multi-Agent Workflows Without the Plumbing](https://lausanne.aitinkerers.org/talks/rsvp_eigQG2pH8qI)

MARSYS is an open-source Python framework for building multi-agent workflows. Define your agents and who talks to who -- the framework handles parallel execution, branch isolation, convergence, context management, and routing automatically. It works with 7+ LLM providers out of the box (OpenAI, Anthropic, Google, local models), ships with ready-to-use agents (browser, file operations, code executor, data analyst), and lets you fine-tune local models directly from execution traces. `pip install marsys` and you're running.

- Event context: AI Tinkerers Lausanne April 2026 Meetup — 2026-04-30 — Lausanne
- Public talk page: https://lausanne.aitinkerers.org/talks/rsvp_eigQG2pH8qI

### [ViteVoyage](https://lausanne.aitinkerers.org/talks/rsvp__1PvyFZ3DEs)

AI powered travel planner

- Event context: AI Tinkerers Lausanne April 2026 Meetup — 2026-04-30 — Lausanne
- Public talk page: https://lausanne.aitinkerers.org/talks/rsvp__1PvyFZ3DEs

### [Lixpi is a visual, node-based workflow engine for building AI image and video generation pipelines](https://toronto.aitinkerers.org/talks/rsvp_SxMp4PNqTxU)

Lixpi is a visual, node-based workflow engine for AI image and video pipelines an infinite canvas where spatial arrangement is the workflow. Instead of writing a workflow DSL or fighting a linear chat prompt, you drop documents, images, and AI chat threads onto the canvas and draw edges between them. The edge graph directly drives context extraction, dependency chains, and execution order for the underlying models. In the demo I'll show live character-consistent image generation via "artifact piping" (one generated image fanned out as edge-context into multiple downstream threads), mid-conversation model switching between OpenAI / Anthropic / Google, and progressive image streaming rendered into the node in real time.

- Event context: AI Tinkerers Toronto - April 2026 - hosted by Shopify — 2026-04-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_SxMp4PNqTxU

### [From Messy Inputs to Reliable Community Data: Human-in-the-Loop AI](https://denver-boulder.aitinkerers.org/talks/rsvp_EuM3A-aBwJ4)

I built Colorado Songwriters Collective, a human-in-the-loop AI workflow that converts messy event/member inputs (DMs, forms, and web pages) into structured, publish-ready community data. In the demo, I’ll show the ingestion pipeline, review checkpoints, and how we keep updates accurate before they go live.

- Event context: AI Tinkerers Denver - April Meeting — 2026-04-27 — Denver
- Public talk page: https://denver-boulder.aitinkerers.org/talks/rsvp_EuM3A-aBwJ4

### [Hive: Local-First AI Gateway](https://bogota.aitinkerers.org/talks/rsvp_ukV86hfl3Q0)

Explore building a local-first AI agent gateway with Bun and SQLite. Learn to orchestrate autonomous agents across multiple communication channels, manage tools, and switch LLM providers seamlessly.

- Event context: AI Tinkerers Bogotá: Demos for builders — 2026-04-23 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_ukV86hfl3Q0

### [How To Sell Cards Online (Fast)](https://nurnberg.aitinkerers.org/talks/rsvp_j3cTo9Vft5s)

Automated trading card identification, grading and pricing using local VLMs (Qwen3.5), MLX, prompt caching and visual chain-of-thought - fast, on consumer hardware, without training data.

- Event context: AI Tinkerers Nürnberg: April Meetup — 2026-04-22 — Nürnberg
- Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_j3cTo9Vft5s

### [Building an AI Cyber Threat Intelligence Dashboard](https://atlanta.aitinkerers.org/talks/rsvp_N1oUwQ-s0Q8)

I built an executive-focused cybersecurity dashboard that aggregates and analyzes threat intelligence from multiple sources to generate a concise, AI-powered daily briefing with verifiable source attribution. In the demo, I walk through the full pipeline—from ingesting data via RSS feeds, web scraping, and MalwareBazaar, to normalizing and enriching indicators, deduplicating and clustering signals, and finally generating a real-time “What’s Happening Today” brief. The system is exposed through backend APIs and a React interface where users can refresh feeds and regenerate structured incident summaries on demand.

- Event context: AI Tinkerers Atlanta: Community Demos & Technical Deep Dives — 2026-04-21 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_N1oUwQ-s0Q8

### [From Chat to CASE: Building an AI Agent That Scouts and Fills Real Complaint Forms](https://singapore.aitinkerers.org/talks/rsvp_y-Gl78fWqSw)

I built Onestop, a chat-first complaint agent that turns a user’s issue into an execution workflow: it extracts the complaint from natural language, plans the escalation path, drafts the complaint email, and for verified portals like CASE Singapore, scouts the live web form and attempts a browser fill through a Form Genome pipeline. The demo is intentionally technical and code-first: a FastAPI orchestrator, structured complaint state, Playwright-based browser execution, and truthful fallbacks when a route is not production-safe.

- Event context: AI Tinkerers Singapore: The Agentic Future & Dev/Eng Workflows — 2026-04-21 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_y-Gl78fWqSw

### [How I Built a Presentation Coaching App in 4 days — With AI as My Engineering Partner](https://hong-kong.aitinkerers.org/talks/rsvp_XloItk_-8gA)

After Chinese New Year this year, I was preparing to teach two modules in the Masters of Economics programme at The University of Hong Kong. My sessions aren't lectures. They involve constant class interaction — students learning by doing, presenting, and getting real-time feedback. Four days before I was due to teach Effective Public Speaking on February 23rd, a thought hit me: what if there was an app for this? Not a slide deck. Not a worksheet. A proper interactive platform that could guide students through the entire process of building a presentation — from structuring their argument to generating slides. That idea became SpeakReady. ## The Approach: Discipline First, Speed Second I could have hacked something together over a weekend. Instead, I chose to treat this like a professional software project — and used AI as my development partner to make that possible. The technology behind SpeakReady is modern (Next.js, React, TypeScript, Firebase, OpenAI), but the real story isn't the tech stack. It's the engineering discipline I was able to maintain, even as a solo builder working at speed. Every feature followed the same rigorous process: define requirements, design the solution, write tests, build it, scan it for quality issues, and ship it through a proper pipeline. AI didn't replace that discipline — it made it achievable. ## Discovery Before Code Before a single line of code is written for any feature, the process starts with discovery. I write detailed design documents that explore the problem, propose two or three architectural approaches with trade-offs, and arrive at a recommended solution. These aren't vague briefs — they specify API contracts, data flows, component hierarchies, and error handling strategies. For example, when I built the AI Wand feature (a button that helps students generate content for any text field using context from their previous work), the design document defined the API request and response shapes, the prompt engineering strategy, rate limiting rules, and exactly how the feature would integrate with five different form types — all before implementation began. Every design document is committed to the repository alongside the code it describes. Requirements aren't lost in chat threads or email chains. They live with the project. ## Testing as a First-Class Citizen Quality isn't something I bolt on at the end. The project uses three layers of quality assurance. **BDD Feature Files.** Every major feature is described in plain-English Gherkin scenarios before development starts. Statements like *"Given I have a team project, When I click Invite, Then I should see the member with Pending status"* define exactly what success looks like — in language anyone can read and validate. **End-to-End Tests.** Fourteen Playwright test suites cover the application's critical flows: authentication, the student dashboard, admin functions, framework forms, AI generation, team collaboration, mobile responsiveness, and more. These tests run against real Firebase emulators, testing the full stack from browser to database. **SonarQube Scans.** Every change is scanned for code quality, security vulnerabilities, and maintainability issues. The scanner analyses the TypeScript source code and flags anything that falls below professional standards. ## Git as the Backbone The project uses Git not just for version control, but as an orchestration layer. Each feature is developed in an isolated worktree — a completely separate working copy of the codebase — so multiple features can progress in parallel without interfering with each other. Branches map to issues. Design documents, feature files, and implementation code all flow through the same pipeline: branch, build, test, review, merge. At last count, the project had managed over twenty parallel worktrees across its development history. That's a level of organisational rigour that would be impressive for a team. For a solo builder with AI assistance, it's transformative. ## What This Means for You You don't need to be a software engineer to take something away from this story. The barrier to building real, professional-quality tools has dropped dramatically. What matters now isn't whether you can write code — it's whether you can clearly define what you want, insist on quality at every step, and use AI to bridge the gap between idea and execution. Four days before I walked into a classroom at HKU, SpeakReady was just a thought. The discipline made it real. The AI made the discipline possible.

- Event context: AI Tinkerers Hong Kong GBA at the Hive: Creative AI Demos & Technical Show-and-Tell — 2026-03-26 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_XloItk_-8gA

### [From Cold Email to Trusted Conversation: How AI Agents Turn Outreach into Revenue](https://seattle.aitinkerers.org/talks/rsvp_Z5K4dyJQ7rE)

This talk covers the architecture of an AI-driven outbound system designed to create highly personalized B2B outreach at scale. I will walk through the design of two agent systems — IRIS, a hyper-personalized email generation engine, and Hermes, a social-channel warming system that leverages the psychological mere exposure effect to increase response rates. IRIS uses Firecrawl to extract structured information from target company websites, Perplexity for real-time research enrichment, and an LLM pipeline that synthesizes this context into personalized outreach messages rendered through React Email templates. The result is emails that read as if they were written by a human founder after researching the company. Hermes operates as a GUI-driven agent that manages warm-up sequences on social platforms, creating lightweight touchpoints before direct outreach. Together, these agents form a two-channel system designed to increase outbound effectiveness in trust-sensitive industries like healthcare. I will walk through the system architecture, data flow, and agent orchestration, including how contextual data is collected, synthesized, and translated into human-like messaging. I will also share early performance results showing how research-driven outreach can significantly outperform traditional cold email strategies.

- Event context: AI Tinkerers Seattle: GTM Track — March — 2026-03-26 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_Z5K4dyJQ7rE

## Related Technologies

- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [Transformers](https://aitinkerers.org/technologies/transformers) ([Markdown](https://aitinkerers.org/technologies/transformers.md)) — 148 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos
- [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos
- [Streamlit](https://aitinkerers.org/technologies/streamlit) ([Markdown](https://aitinkerers.org/technologies/streamlit.md)) — 89 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 220 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 99 public demos
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 174 public demos

## More Results

- Next: https://aitinkerers.org/technologies/openai-api.md?page=2