# Llama 3 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/llama-3
> Markdown URL: https://aitinkerers.org/technologies/llama-3.md
> Technology record last updated: 2026-02-23T14:36:31Z
> Generated: 2026-09-21T05:37:52Z

Meta's state-of-the-art, openly available Large Language Model: Llama 3 delivers superior performance with 8B and 70B parameter versions.

Llama 3 is Meta's next-generation LLM, setting new benchmarks for openly available models. We released initial versions at 8B and 70B parameters, both instruction-tuned for peak performance (outperforming models like Gemini Pro 1.5 and Claude 3 Sonnet on key industry metrics). The model was trained on a massive 15 trillion token dataset (7x Llama 2's data) and features a 128,000-token vocabulary and 8,192-token context length: this architecture enables enhanced reasoning and multilingual capabilities across over 30 languages. Llama 3 is designed for scale and efficiency, integrating Grouped Query Attention (GQA) for faster inference.

- Official technology site: https://llama.com
- Public AI Tinkerers demos and talks: 38
- Result page: 1 of 2

## Recent Public Talks and Demos

### [GitFlix](https://dubai.aitinkerers.org/talks/rsvp_NOm-XVCUWNY)

GitFlix is an AI-powered developer tool that transforms any GitHub repository's commit history into a cinematic documentary-style video narration. For the demo, I'll show a working system, you paste a GitHub repo URL, the backend ingests the full commit history via the GitHub API, an analytics engine detects contribution eras, character arcs, and hero commits, a LangChain agent generates a structured script and Remotion renders it into an actual video with scenes, narration and transitions. I'll walk through the live app, the LangChain agent reasoning, and the architecture end to end.

- Event context: AI Tinkerers Dubai - May Demo Day — 2026-05-23 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_NOm-XVCUWNY

### [Transformer-Diffusion model for molecular battery material generation](https://dubai.aitinkerers.org/talks/rsvp_SK0KgeEQ2Rc)

I built Simer Energy, an end-to-end generative AI pipeline that uses a hybrid Transformer-Diffusion architecture to autonomously design, physically relax and thermodynamically validate novel battery materials from scratch. For the demo, I will execute a terminal-based run of the by inputting strict material constraints (e.g., elemental bounds for a cobalt-free transition metal oxide, target stoichiometry, and symmetry parameters) into a fine-tuned model. I’ll show how the Transformer maps these constraints into a discretespace groups and passes it as a conditioning vector to a diffusion model. You will see the model denoise the 3D spatial atomic coordinates, followed by the critical "zero-strain" and then passing the raw generated structure directly into a Universal Machine Learning Force Field (CHGNet) to instantly relax the atomic coordinates, bypassing days of expensive DFT calculations and then run the relaxed structure through ALIGNN to validate its Energy Above Hull, resulting in a mathematically viable file generated in under three minutes.

- Event context: AI Tinkerers Dubai - May Demo Day — 2026-05-23 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_SK0KgeEQ2Rc

### [Ask the Oracle Before You Decide : Simulating the Future with LLM Agents](https://toronto.aitinkerers.org/talks/rsvp_VTeGGfFVq8g)

Pythia is an LLM-powered simulation engine that models how individual cognitive biases and crowd psychology interact to shape real-world decisions, before those decisions are made. For the demo: you give it a scenario (a market move, a policy choice, a personal decision under pressure), and it spins up a cast of behaviorally-distinct AI agents, each carrying a named bias like Loss Aversion, FOMO Drive, or Anchoring and drops them into a live crowd field. You watch opinion dynamics unfold tick by tick. At a critical moment, one agent is sent to the Temple of Learning: their behavior is evaluated, their rules are amended, and they re-enter the simulation. Run over run, the system gets more accurate. The visualization shows all of it : the crowd state, the agent trajectories, the oracle's intervention, the improving accuracy curve.

- Event context: AI Tinkerers Toronto - April 2026 - hosted by Shopify — 2026-04-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_VTeGGfFVq8g

### [Kokoro on the web](https://la.aitinkerers.org/talks/rsvp_iMNQYyRB6MM)

Expanded my iOS app for summarizing any article into 3 levels of detail, into a web app so Android users can use it. To save money I’ve got a free (for low usage) PaaS running Kokoro (the same TTS I’m running directly on the iPhone). Shocking how much cheaper it is, even at usage beyond free level. Also found my existing prompts (Llama 3.2 and Apple Intelligence on iOS, as well as Claude Sonnet via API) have consistent accuracy issues, which I’m still working on.

- Event context: AI Tinkerers LA: February Builder Meetup & Live Demos — 2026-02-24 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_iMNQYyRB6MM

### [Building a Real-time Voice Agent with Cloudflare's Edge Stack](https://montreal.aitinkerers.org/talks/rsvp_FZMBRFtgd6Q)

Live demo of a sales pitch coaching app built entirely on Cloudflare: Durable Objects for stateful WebSocket sessions, Workers AI for real-time transcription and LLM inference, Vectorize for RAG, and R2 for document storage. I'll walk through the architecture decisions, show how structured extraction beats naive RAG chunking, and demo the app coaching a live pitch with realtime insights and post-session scoring.

- Event context: AI Tinkerers Montreal - January 2026 Meetup at Ateko — 2026-01-21 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_FZMBRFtgd6Q

### [Agentic AI in Action – Building Multi-Step Decision-Making AI Agents with LangGraph](https://pune.aitinkerers.org/talks/rsvp_fSmJM9LqFwk)

2025 is the year of Agentic AI — where LLMs don’t just answer questions, they think, plan, and act. In this session, I’ll demonstrate how to build an AI agent that can reason, decide, and execute multi-step workflows using LangGraph and open-source LLMs. We’ll cover: Why Agentic AI is the next leap beyond chatbots Architecting stateful decision flows with LangGraph Live demo: An AI financial analyst that fetches data, analyzes it, and produces an actionable report — all autonomously.

- Event context: AI Tinkerers Pune - Meetup — 2025-08-23 — Pune
- Public talk page: https://pune.aitinkerers.org/talks/rsvp_fSmJM9LqFwk

### [Beyond One-Size-Fits-All: Building Intelligent LLM Selection Systems](https://sydney.aitinkerers.org/talks/rsvp_NOKtH4wA9Vs)

The presentation will demonstrate NVIDIA's LLM Router Blueprint - a production-ready solution that intelligently routes user prompts to the most appropriate Large Language Model based on task classification and complexity analysis. We'll explore how this OpenAI-compatible routing system solves the common dilemma of choosing between accuracy, speed, and cost in modern AI applications. The session will cover: Live Demo: Watch the router automatically classify prompts (code generation → DeepSeek, general Q&A → Llama 70B, simple rewrites → Llama 8B) and route them accordingly Architecture Deep Dive: Understanding the three-component system (Router Controller, Router Server with Triton, Downstream LLMs) Real-World Impact: Cost optimization strategies and performance benchmarks Hands-On Implementation: Step-by-step deployment using Docker Compose and Kubernetes Customization Possibilities: Creating custom routing policies for domain-specific use cases Attendees will leave with practical knowledge of implementing intelligent LLM routing in their own applications, complete with code examples and deployment configurations.

- Event context: AI Tinkerers – Sydney Inaugural Meetup · 20 August 2025 — 2025-08-20 — Sydney
- Public talk page: https://sydney.aitinkerers.org/talks/rsvp_NOKtH4wA9Vs

### [DevOps Meets AI: Multi-Agent Incident Resolution in Minutes, Not Hours](https://hamburg.aitinkerers.org/talks/rsvp_CgDF8DKg9Jw)

I will demo Hyground, our AI copilot for DevOps that resolves critical incidents in minutes instead of hours. The session will cover a live interaction with our tool, while talking about its architecture and how it provide the output shown in the interaction (i.e., multi-agent LLM design, the data-flow and integrations)

- Event context: AI Tinkerers Hamburg #3 - August 14 — 2025-08-14 — Hamburg
- Public talk page: https://hamburg.aitinkerers.org/talks/rsvp_CgDF8DKg9Jw

### [Beyond the Prompt: Building Chatbots That Control Your UI](https://hamburg.aitinkerers.org/talks/rsvp_g8EA-mgQf0U)

AI-Powered UI Control: Integrate a chatbot that can directly manipulate your frontend application. Interactive In-Chat Elements: Use LLM tools to display visual components and commands for users to interact with. 🤖 Automatic Page Context: Instantly provide the AI with on-screen context for smarter, more relevant interactions.

- Event context: AI Tinkerers Hamburg #3 - August 14 — 2025-08-14 — Hamburg
- Public talk page: https://hamburg.aitinkerers.org/talks/rsvp_g8EA-mgQf0U

### [Building an Agentic AI System That Replaces Digital Ad Agencies: Multi-Stage LLM Architecture with Recursive Planning, Multimodal Analysis, and Novel Optimization Strategies](https://orange-county.aitinkerers.org/talks/rsvp_y1ihXS44YRA)

I'll demonstrate how I built AdRes, a sophisticated agentic AI system that eliminates digital ad agencies through advanced multi-stage Lambda architecture. The demo will showcase our recursive planning system that uses Anthropic Claude 3.5 Sonnet with custom fine-tuned prompts, vector embeddings for campaign similarity matching, and a multimodal creative analysis pipeline using OpenCV and computer vision. I'll walk through the code that powers our unified context system, agentic workflow with tool selection and self-correction, and real-time campaign optimization engine that processes complex multi-source data analysis.

- Event context: AI Tinkerers - Orange County Meetup- Thursday July 31st 2025 — 2025-08-01 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_y1ihXS44YRA

### [Aura: A Locally Hosted AI Gaming Companion](https://dc.aitinkerers.org/talks/rsvp_PPJAfIPNvoQ)

Aura is a locally hosted AI companion that observes live gameplay, interprets on-screen activity, and interacts with players through voice-based commentary. It combines screen capture, computer vision, speech recognition, and voice synthesis into a modular system designed for real-time operation without relying on cloud services. Aura adapts to different games, learns from user feedback, and allows dynamic personality and voice customization

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

### [PentestIA: Automatizando Pruebas de Penetración con IA y MCP](https://manizales.aitinkerers.org/talks/rsvp_jVaW-NIuQUQ)

PentestIA, un sistema innovador que combina inteligencia artificial con el protocolo MCP (Model Context Protocol) para automatizar pruebas de penetración web. El sistema utiliza un motor de decisiones basado en Llama 3.2 que analiza endpoints automáticamente y coordina múltiples herramientas especializadas (XSS, SQLi, reconnaissance) para realizar evaluaciones de seguridad completas.

- Event context: 🚀 ¡Quinto Encuentro de AI Tinkerers Manizales! 🤖 — 2025-06-25 — Manizales
- Public talk page: https://manizales.aitinkerers.org/talks/rsvp_jVaW-NIuQUQ

### [Slop-Free Social Posts](https://nashville.aitinkerers.org/talks/rsvp_uN7sMMBIR8k)

AI can help you minimize time spent drafting social media posts, but you know everyone can smell an AI-generated LinkedIn cringepost from a mile away. Let's build a simple workflow that preserves your voice by repackaging your human-authored content into something suitable for a new medium. Using multiple prompt variants and an LLM-as-judge evaluation step, we'll generate slop-free drafts you can proudly share on social media.

- Event context: AI Tinkerers Nashville – June 23rd, 2025 — 2025-06-23 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_uN7sMMBIR8k

### ["Sports Videos Understanding at Scale" OR "Video Runner Bib OCR detection"](https://montreal.aitinkerers.org/talks/rsvp_IccvgKkVEhA)

there are two things I worked on in Q1 and 2024Q4 that might be interesting: 1. Using VLM to create a Visual Q&A using RAG and also using it for "guided" highlight detection 2. I also tried using the large context window offered in Gemini 2.0 Flash Thinking to read marathon runners' bib

- Event context: AI Tinkerers Montreal - May 2025 Meetup at LightSpeed — 2025-05-07 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_IccvgKkVEhA

### [Can Identity be fine-tuned with QLoRA for an AI Vtuber?](https://quito.aitinkerers.org/talks/rsvp_ihNPM41KEw4)

Can Identity be fine-tuned with QLoRA for an AI Vtuber? In this technical demonstration, I'll walk you through the step-by-step creation a real-time interactive VTuber powered by a base LLM (LLaMA 3.2) 3B*, fine-tuned with QLoRA and the Unsloth framework. You'll see firsthand how we went beyond typical "instruction-following" models to craft a uniquely creative and reflexive virtual personality. I'll share: How we efficiently applied LoRA layers for lightweight, GPU-friendly fine-tuning. Deep insights into dataset preparation, custom prompt engineering, and careful handling of conversational structure to create a convincingly human-like personality. Technical challenges overcome, including managing VRAM constraints (on an RTX 3060) through quantization, CPU offloading, and careful gradient management.

- Event context: AI Tinkerers - Quito Primer Meetup (Abril) — 2025-04-24 — Quito
- Public talk page: https://quito.aitinkerers.org/talks/rsvp_ihNPM41KEw4

### [Automatic Data Seeding for Testing your Apps](https://sf.aitinkerers.org/talks/rsvp_nZetn3Pbp_w)

This project is a Python-based agent that generates synthetic data modeled after an existing database. It first analyzes the structure and statistical properties of the stored information, identifying key attributes such as data types, distributions, and relationships between fields. It then generates new entries that maintain the patterns of the original dataset while ensuring all data remains synthetic and non-sensitive. Using techniques such as rule-based constraints, probabilistic sampling, and structured formatting, the agent creates realistic datasets suitable for application testing, load simulations, and controlled experiments. It supports customization for specific formats, enforcing consistency in unique identifiers, categorical variables, and numerical ranges. The goal is to provide developers with a reliable and automated way to populate test environments with useful, structured data that behaves like real-world input without the risks of using actual production data. For future iterations, the project could integrate AI-driven data augmentation techniques or pre-trained language models to enhance data variability and contextual accuracy.

- Event context: AI Tinkerers - San Francisco - February 2025 Demos + Science Fair — 2025-02-28 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_nZetn3Pbp_w

### [Automating the art of deception for the greater good](https://dublin.aitinkerers.org/talks/rsvp_OljSLlzDSv4)

In this talk, I will demonstrate how AI is revolutionizing phishing lure generation at scale, eliminating the need for manual crafting and HTML expertise while making attacks more targeted and convincing than ever before. I will showcase how my AI-powered lure generator can mass-produce highly customized phishing lures using large language models (LLMs)—automating the entire process from text generation to HTML modification. With just a few inputs, AI can generate realistic, organization-specific phishing emails that mimic legitimate communication, allowing for adaptive and hyper-targeted phishing simulations. Additionally, I will explore how a secondary LLM can modify the HTML structure of emails automatically, ensuring that non-technical users can create polished, professional-looking phishing lures without needing to code. This means: ✅ No HTML knowledge required—AI modifies templates dynamically ✅ Mass generation of phishing lures—scaling deception effortlessly ✅ Extremely targeted attacks—customized based on organization, industry, or individual profiles By the end of this talk, you’ll understand how AI-driven phishing lures are reshaping social engineering tactics, how automation removes traditional barriers like coding expertise, and what this means for both attackers and defenders in cybersecurity.

- Event context: AI Tinkerers - Dublin Event (February) — 2025-02-24 — Dublin
- Public talk page: https://dublin.aitinkerers.org/talks/rsvp_OljSLlzDSv4

### [Sakhr](https://dubai.aitinkerers.org/talks/rsvp_7XBGehpeVwc)

A student assistant app that can generate notes, reminders, and quizzes from lecture transcription

- Event context: AI Tinkerers - Dubai Meetup #5 (February) — 2025-02-05 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_7XBGehpeVwc

### [Read an AI's Mind](https://london.aitinkerers.org/talks/rsvp_7nDnzZZ4_sA)

I've been working on classifiers that use internal activations of a GPT to predict whether the LLM is hallucinating, and would like to show some results on that work. I will discuss how I instrumented the Llama 3.2 3B parameter model, what kinds of questions worked well to trigger hallucinations regularly, and how I built the classification model.

- Event context: AI Tinkerers London - January Meetup — 2025-01-22 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_7nDnzZZ4_sA

### [Genatron](https://chicago.aitinkerers.org/talks/rsvp_nO5i7_l8KDU)

Current no-code and low-code tools require users to think like developer and have a learning curve. Genatron allows you to build entire admin panels, internal tools and database apps using plain English requirements. Users can have a working build of their app within 5 minutes with support for record management, reports, dashboard metrics/charts, role-base access controls and more.

- Event context: AI Tinkerers Chicago January Meetup — 2025-01-14 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_nO5i7_l8KDU

### [ASISTENTE IA PARA PRACTICAR INGLÉS](https://medellin.aitinkerers.org/talks/rsvp_O5tPpo17Miw)

Esta aplicación de asistente de voz basada en IA permite una conversación en tiempo real entre los usuarios y un modelo de inteligencia artificial. Diseñada para practicar los contenidos del curso de inglés de manera interactiva, la aplicación emplea tecnologías avanzadas de procesamiento de audio y lenguaje natural para ofrecer una experiencia fluida y natural. La aplicación funciona conectando un frontend diseñado con React para la interfaz gráfica del usuario con un backend que utiliza el modelo Whisper para la transcripción de audio en tiempo real, LLaMA 3.2 1B para la generación de respuestas, y Edge TTS para la síntesis de voz. Además, el backend se conecta directamente a la aplicación Ollama a través de su API utilizando un localhost, lo que facilita el procesamiento eficiente de las interacciones. Los usuarios pueden iniciar una conversación a través de su micrófono, y el sistema convierte su voz en texto, procesa la información y devuelve una respuesta auditiva utilizando tecnologías de síntesis de voz. Esto permite una comunicación fluida donde el modelo responde a preguntas y refuerza el aprendizaje de los temas vistos en el curso. Esta herramienta representa un enfoque innovador para apoyar el desarrollo de habilidades lingüísticas, utilizando modelos de machine learning para crear una práctica interactiva, personalizada y completamente automatizada.

- Event context: AI Tinkerers Medellín #8 - 5 de Diciembre — 2024-12-05 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_O5tPpo17Miw

### [OCR 2.0, Using Vision Language Models for instruction augmented OCRs](https://bengaluru.aitinkerers.org/talks/rsvp_iI8E7i1YB6E)

OCR is almost a solved problem but not really a generalizable problem. Although I am not an industry expert, but from talking to some expert I realized that classical (Object detection / text-recognition / rule based) OCRs normally parses the whole document and returns a very "less organized" results. Lot of manual post processing are involved on these kind of OCRs. The level of post processing / hardcoding logic for a family of documents rises with the increase in complexity of the document (example: if document contains combination of tables / images etc). With rise of LLMs and Vision Language Models (VLMs), the above problems can be solved and can be generalized over a range of documents. Last week, I started this new side project of mine, of building a more generalized OCR pipeline, where user will upload the document and also provide the expected output schema. The pipeline will do the OCR and would structure the result adhering to the uploaded schema. I tried over some range of documents (complex documents with tables, invoices and multi lingual documents). Now I do not want to make this another Open AI wrapper software, for several reasons: - For enterprise focussed documents, invoices might contain lot of PIIs and user would not be comfortable giving it to a third party client. - I did some bunch of experiments, and from there, I learned, I can achieve a very good pipelines with models < 7B parameters. I have been using ensembling approaches and it really works. For instance, there is a recent model called GOT-OCR 2.0, which gives awesome result but it is based on Qwen 0.5B. More open source models like InternLM, Qwen models, Llama 3.2 vision are also amazing and adheres with the schema. - It also gives me a full flexibility for furthur fine-tuning models on very complex documents where it fails to give results. Speaking of fine-tuning, I surely have faced challenges. For example, I have been fine-tuning GOT-OCR for a less known language, and I learned that it got overfitted on my training dataset and could not generalize over anything outside the training dataset distribution. Also for fine-tuning, generating data samples is also another challenge. In this talk I will be sharing my above learnings and my roadmap in more details and lead to an open discussion. ps: I will show the demo while doing the presentation

- Event context: AI Tinkerers Bengaluru - December - RSVP REQUIRED — 2024-12-05 — Bengaluru
- Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_iI8E7i1YB6E

### [Building a 68,000+ Element Graph Database: Generative AI Meets Ground-Truth Vetting: A Technical Deep Dive](https://boston.aitinkerers.org/talks/rsvp_QnatrFsN4jk)

Abstract: Can we create a valid dataset with over 68,000 elements, built, cleansed, and vetted using generative AI and standard CPU logic? In this talk, I will share how this can be achieved by integrating local and API-based Large Language Models (LLMs) with a Neo4j graph database, anchored to ground truths from Wikidata. Additionally, this talk will briefly show how the IDE Cursor AI was used in a 'one shot' fashion to create the node scripts used for this project. What You’ll Learn: • Node.js Scripts for LLM Interactions: I’ll walk you through the Node.js scripts written in JavaScript that automate the solicitation of responses from LLMs. Specifically, we’ll see how the Llama 3.1 model, running locally with Ollama, was used to generate a set of idealized features for each job task. • Leveraging Perplexity API for Solution Matching: Discover how I utilized the Perplexity API to find products or solutions that match the idealized features generated. We’ll delve into the code that handles API requests and processes the responses. • Data Anchoring with Wikidata API: Learn how I ensured data quality by anchoring information to ground truths using the Wikidata API. I’ll show you how I matched solutions from Perplexity responses to Wikidata Entity IDs as a first pass for populating the Neo4j database. • Neo4j Graph Database Schema: I’ll provide an in-depth look at the Neo4j graph database schema, explaining how Product and Company nodes are connected. We’ll explore how content from Perplexity enriches the relationships in the graph. • Building the App with SvelteKit: See how the front-end application was built using SvelteKit. I’ll guide you through the codebase, highlighting how the app interacts with the Neo4j database to present data to users. Technical Challenges and Solutions: • Cost Reduction with Local LLMs: Understand how running the Llama 3.1 model locally with Ollama helped reduce costs associated with large-scale data generation. • Data Quality Assurance: Learn about the strategies employed to cleanse and vet the data, including anchoring to Wikidata and handling discrepancies between sources. • Integration of Multiple APIs: See how I managed the complexities of integrating responses from different APIs (Perplexity and Wikidata) into a cohesive dataset. Live Demonstration: • Code Walk-Through: I’ll live-demo sections of the code, explaining how each part contributes to the overall goal. This includes Node.js scripts for LLM interactions, API integrations, and SvelteKit components. • Interactive Exploration: Attendees will have the opportunity to see the app in action, exploring the dataset of 850 jobs and their associated tasks and solutions.

- Event context: AI Tinkerers Boston November Meetup — 2024-11-25 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_QnatrFsN4jk

### [Hello Ichigo - Voice AI you own](https://singapore.aitinkerers.org/talks/rsvp_2czH_aSVN8c)

Sharing our progress on Ichigo, our voice for the future of assistants. Now live on a 3090 GPU - Ichigo v4 has better multi-turn conversations, longer context length, and is smarter (MMLU score 64.66 vs 42.11 in base-v0.3). It better handles noisy environments. Also introducing Mini Ichigo, based on Llama3.2-3B (59.61 MMLU).

- Event context: AI Tinkerers Singapore: 3rd Meetup - November 19th, 2024 — 2024-11-19 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_2czH_aSVN8c

## Related Technologies

- [Ollama](https://aitinkerers.org/technologies/ollama) ([Markdown](https://aitinkerers.org/technologies/ollama.md)) — 77 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [Mistral](https://aitinkerers.org/technologies/mistral) ([Markdown](https://aitinkerers.org/technologies/mistral.md)) — 24 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 219 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 105 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [AWS Bedrock](https://aitinkerers.org/technologies/aws-bedrock) ([Markdown](https://aitinkerers.org/technologies/aws-bedrock.md)) — 9 public demos
- [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [GPT-4o](https://aitinkerers.org/technologies/gpt-4o) ([Markdown](https://aitinkerers.org/technologies/gpt-4o.md)) — 57 public demos
- [LangGraph](https://aitinkerers.org/technologies/langgraph) ([Markdown](https://aitinkerers.org/technologies/langgraph.md)) — 67 public demos
- [Neo4j](https://aitinkerers.org/technologies/neo4j) ([Markdown](https://aitinkerers.org/technologies/neo4j.md)) — 29 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [OpenAI Whisper](https://aitinkerers.org/technologies/openai-whisper) ([Markdown](https://aitinkerers.org/technologies/openai-whisper.md)) — 10 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [QLoRA](https://aitinkerers.org/technologies/qlora) ([Markdown](https://aitinkerers.org/technologies/qlora.md)) — 4 public demos
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos

## More Results

- Next: https://aitinkerers.org/technologies/llama-3.md?page=2