# Python Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/python
> Markdown URL: https://aitinkerers.org/technologies/python.md
> Technology record last updated: 2026-09-18T15:13:57Z
> Generated: 2026-09-20T14:47:10Z

Python: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.

Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .

- Official technology site: https://python.org
- Public AI Tinkerers demos and talks: 662
- Result page: 1 of 28

## Recent Public Talks and Demos

### [Training/Generating Absurd Cat Standup Videos](https://la.aitinkerers.org/talks/rsvp_7-heCmu8l0U)

I will be using Python/LLAMA-3 model to train a Seinfeld Style Monologue Generating LLM model and use Veo 3 to automatically make Absurd Cat Standup Videos. -I first scraped all Seinfeld scripts from https://www.seinfeldscripts.com/ -I captured/cleaned/formatted monologue data from the scraped Seinfeld scripts. -I used Python/Ollama to train the Llama 3 8b model to make an LLM that can generate seinfeld style monologue by subject. -I used the output of the trained LLM to make cat standup videos through Veo 3.

- Event context: Aug 16 - AI Tinkerers LA: Beauty, Bytes, and Venice Beach Vibes 🌊✨🤖 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_7-heCmu8l0U

### [Wittgenlab, creando un framework para evaluar llms](https://bogota.aitinkerers.org/talks/rsvp_DQbVYpY7uWA)

Wittgenlab surgió de la busqueda de crear un framework que permitiera evaluar de forma efectiva los agentes y modelos desplegados, usando conocimiento de varios papers y la experiencia construí una solución que es la base para evaluar modelos y que cada dia crece más, además de open source

- Event context: AI Tinkerers Bogotá - Julio 24 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_DQbVYpY7uWA

### [From idea to production in one loop: how a PM, a data bot and a coding agent ship at Fasset.](https://lahore.aitinkerers.org/talks/rsvp_c7poPoSKGUM)

Fasset is a global stablecoin backed neobank which gives access to digital banking and wealth building tools. It serves the freelancer, remote workers many of them are young professionals in Pakistan. This demo will be a product manager's view of how an idea reaches production with AI at every step, in three demos: prototype first (the team builds clickable prototypes with Claude instead of writing PRDs); decide with data (Dasset, an internal Slack bot that answers plain-English questions against a governed warehouse layer); and ship (Fasset Harness, a Claude Code plugin that makes coding agents work from human-reviewed test trees).

- Event context: AI Tinkerers Lahore: September 19, 2026 — 2026-09-19 — Lahore
- Public talk page: https://lahore.aitinkerers.org/talks/rsvp_c7poPoSKGUM

### [Local AI on anything with NobodyWho](https://copenhagen.aitinkerers.org/talks/rsvp_eeot-Z52CbQ)

An open-source library for running local LLMs on any hardware: custom inference engine in Rust with bindings to 6 languages, builds for 7 operating systems, and hardware accelerating on anything.

- Event context: September Demo Night — 2026-09-16 — Copenhagen
- Public talk page: https://copenhagen.aitinkerers.org/talks/rsvp_eeot-Z52CbQ

### [Implementing a multi-agent blog post writer using Microsoft Agent Framework](https://boston.aitinkerers.org/talks/rsvp_i1qCN9asMtA)

This application demonstrates concepts covered in over 30 blog posts on Microsoft Agent Framework and related technology. The app generates meaningful blog posts on virtually any topic. The Blogger agent coordinates, the Research agent goes out to the web to bring back relevant information, the Author agent writes a draft post and the Reviewer agent evaluates the post and approves or sends it back to the Author for improvement. I will demonstrate live code and cover a variety of related topics such as Logging, OpenTelemetry, Middleware, token usage limits, and long-term memory approaches in Microsoft Agent Framework

- Event context: Back from Summer: AI GTM Builders — 2026-09-03 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_i1qCN9asMtA

### [How to beat any benchmark with recursive self improvement](https://amsterdam.aitinkerers.org/talks/rsvp_PpT8TxQ4mtA)

I did build a system that autonomously evaluates and improves agents. The approach is backed by this paper: https://arxiv.org/abs/2603.28052 I applied this to a known agentic benchmark called Tau-bench from Sierra.ai. As a result I'm able to beat the benchmark by 10% on multiple domains.

- Event context: AI Tinkerers Demo Night: Agents in Various Forms — 2026-09-03 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_PpT8TxQ4mtA

### [Learn Anything by Doing: An Agent That Teaches, a Grader That Can't Flatter You](https://hong-kong.aitinkerers.org/talks/rsvp_9jqGP6qJZHg)

Carpenter is a tool for learning by doing: you tell your AI agent what you want to master, it drafts a course outline for your approval, renders Jupyter notebooks with practice stubs and quizzes — and the second you hit Run, you get an instant, honest per-case PASS/FAIL. The agent teaches; carpenter grades. The key trust move: grading is locked to an answer key the agent can't see at grade time (lesson verify against an authored reference solution), and the grading helper is structurally verification-only — it can never print expected. A pass is a real pass, not the AI being nice to you. Live demo, two beats. Beat 1 (the main event): from "I want to learn X" to a graded notebook in minutes — agent drafts the plan, I approve it, a rendered notebook appears (SQLite is the source of truth; notebooks are just views), I fill in a practice stub, Run, instant feedback, then progress summary showing exactly what's done and where I'm stuck. Beat 2 (the twist, short): this tool is itself built by the same kind of loop — I'll add a command via an agent and show the build refusing to compile until the docs and tests exist. The learning tool dogfoods its own philosophy.

- Event context: AI Tinkerers Hong Kong: August Meetup with OAX Foundation and GMAsia — 2026-08-31 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_9jqGP6qJZHg

### [Salve tudo o que puder: buscador local que acha qualquer coisa da minha vida em 25ms](https://curitiba.aitinkerers.org/talks/rsvp_htrQvE_vtiI)

lux_find is a local full-text search index for everything you already have on disk: markdown notes, source code, and exported chat histories with coding agents. One SQLite file, BM25 ranking over FTS5, no server, no cloud, no runtime dependencies — about 2,000 lines of standard-library Python you can read in an afternoon. lux-find init points it at your folders, index builds or refreshes the index in seconds, find answers in milliseconds, and find --json gives a coding agent the same results as context. Demoed live at AI Tinkerers Curitiba as "Buscador Local: Salve Tudo".

- Event context: AI Tinkerers Curitiba: Encontro de Agosto (no EBANX) — 2026-08-26 — Curitiba
- Public talk page: https://curitiba.aitinkerers.org/talks/rsvp_htrQvE_vtiI

### [From 1,157 handwritten forms to one geological fact: a 25 m pile-driving limit](https://curitiba.aitinkerers.org/talks/rsvp_nt6LgCapvyQ)

A resumable extraction pipeline that turned 1,157 handwritten pile-driving field bulletins — scanned into 1,400+ messy PDFs — into a clean, georeferenced dataset, and then into engineering knowledge. The arc is the point: reports → data → knowledge. Live, I'll show the raw handwritten forms going in (smudged, non-standard, with voided sheets and unrelated pages mixed in), parallel subagents transcribing each to JSON, and the consolidated 1,157-record CSV driving an interactive report — histograms, box plots, an E×N heatmap, and a 3D scatter of 627 georeferenced piles. Then the payoff: those production-control reports became a technical and geological analysis instrument. Aggregated, the field data no single form could show revealed a consistent practical driving limit of ~25 m for the site (mean driven depth 24 m) — a hard geological fact that makes the next foundation estimate far more assertive. The dataset is a real completed job: 1,000+ pre-cast concrete piles driven over six months for a grain terminal in southern Brazil.

- Event context: AI Tinkerers Curitiba: Encontro de Agosto (no EBANX) — 2026-08-26 — Curitiba
- Public talk page: https://curitiba.aitinkerers.org/talks/rsvp_nt6LgCapvyQ

### [AI-utomated open source project](https://missoula.aitinkerers.org/talks/rsvp_8vucNXtGqcw)

I use scheduled loops with Claude Code to build, maintain, and enhance the myIO project for data visualization

- Event context: AI Tinkerers – Missoula Inaugural Meetup · 26 August 2026 — 2026-08-26 — Missoula
- Public talk page: https://missoula.aitinkerers.org/talks/rsvp_8vucNXtGqcw

### [Create Your Own DeepSeek Moment](https://nyc.aitinkerers.org/talks/rsvp_UswbXaI7O_0)

I built an autonomous loop that tests and proves small models (finetuned in some cases) can replace large ones on real traffic before safely rerouting to them. Live I'll show the decision engine choosing which work to optimize, fine-tuning candidate models, clustering traffic to anonymize data, and if time allows examples of a small model beating a large one on specialized work, an eval that fails and keeps the large model live, and the prove-gate thresholds that make it production-safe.

- Event context: August Demo Day ft Runpod, Veris, Openrouter, — 2026-08-19 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_UswbXaI7O_0

### [Teaching an LLM to be an interior designer](https://nyc.aitinkerers.org/talks/rsvp_G0dtIg_V-Dw)

A pipeline that turns a LiDAR room scan into art-placement decisions — which wall, what size, what art — by converting usdz geometry into per-wall design constraints that drive image generation, with a vision-LLM design critic whose judgments are verified, calibrated, and used to teach the deterministic scoring engine. Live, I'll walk the raw scan data (the LiDAR mesh and its JSON), the geometry visualizers that turn planes into design constraints, and the tooling we use to calibrate the critic and verify its judgments against the engine.

- Event context: August Demo Day ft Runpod, Veris, Openrouter, — 2026-08-19 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_G0dtIg_V-Dw

### [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

### [How I spent $800 Building a Rat Terminator with ML (Instead of Hiring an Exterminator)](https://raleigh.aitinkerers.org/talks/rsvp_GQC-HE7VnGs)

There is a slide deck here: https://westcot.io/talks/you-dirty-rat/ Have a live version I may modify for in person demo that solves one of the problems with the stereo vision discussed in the deck. It's hard to do without slides as it's a narrative of starting with an automated trap and all the points (building bearings and movement with all the things I learned along the way).

- Event context: AI Tinkerers Raleigh Meetup — August 12, 2026 — 2026-08-12 — Raleigh
- Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_GQC-HE7VnGs

### [Your AI agent will lie to you: the "say-do gap" and a deterministic fix](https://dubai.aitinkerers.org/talks/rsvp_eS1r2yCCqzw)

ReceptionAI is a production AI receptionist for real-estate agencies — an LLM agent that qualifies leads, books viewings, and follows up over WhatsApp via function-calling. Live, I'll run a real after-hours enquiry through it end-to-end (message → qualification → booked viewing, with the tools firing in real time), then open the hood: the tool-calling loop, the deterministic "lead-capture safety net" that guarantees a lead is never lost even when the model skips a tool call, and how I verified it against the database. Real system, real code, real logs — not a canned video.

- Event context: AI Tinkerers Dubai — August Demo Day — 2026-08-08 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_eS1r2yCCqzw

### [EduSense: A Multi-Agent AI Platform for Emotion-Aware Education](https://dubai.aitinkerers.org/talks/rsvp_KyNKCO_MVFc)

EduSense is a multi-agent AI education platform built for the Kaggle AI Agents Capstone. It uses DeepFace for real-time facial emotion analysis via webcam, and 7 specialized agents — orchestrated by a central workflow — to generate lessons, quizzes, flashcards, and PDF reports for instructors. The backend runs on FastAPI with PostgreSQL. I'll demo the live agent pipeline: emotion capture, the sequential agent workflow, and the instructor dashboard.

- Event context: AI Tinkerers Dubai — August Demo Day — 2026-08-08 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_KyNKCO_MVFc

### [Agents Are Not Service Accounts: Post-Quantum Channels and Zero-Knowledge Delegation Between AI Agents, Live](https://dubai.aitinkerers.org/talks/rsvp__l-10tNvOo4)

Agent Trust Lab is a live simulator where two AI agents establish a quantum-resistant channel and prove delegated authority without revealing credentials. The scenario: a user delegates vacation booking up to a EUR 3,000 budget, and the agent proves that authorization to a counterparty without exposing who the user is or what else it may do. The same exchange runs side by side across three models: classical (X25519 + bearer token), PQC without ZKP (X25519 + ML-KEM-768 hybrid), and PQC + ZKP (Schnorr proof over the encrypted link), so you can watch exactly where each pattern leaks. It runs live at trustlab.mahasbini.org: the three-model exchange, a quantum-attack toggle that breaks the classical session while the hybrid one holds, and an audit-receipt tamper test where editing any bound field (responder, negotiated group, session commitment) invalidates the receipt in front of you. The demo closed with the real thing in production: a self-hosted video-conferencing stack negotiating X25519MLKEM768 on TLS 1.3 (OpenSSL 3.5), inspected live from the browser. No slides, no LLM on stage: this is the layer your agents stand on.

- Event context: AI Tinkerers Dubai — August Demo Day — 2026-08-08 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp__l-10tNvOo4

### [When the AI Judge Is Wrong: A Verifiable Floor for LLM Evaluations](https://dubai.aitinkerers.org/talks/rsvp_e3czbFAtNPA)

I am building Lithrim, an open-source eval harness that pairs a configurable LLM judge council with a deterministic grounding floor. The grounding floor changes an outcome only when it can prove the change against an external oracle. Live on the real UI, I'll grade a few AI-generated clinical notes (no real patient data) using a two-judge council. The judges catch the planted defects, but they also over-flag, so recall is high and precision is low. The floor then clears a provable false positive through a grounding check against a SNOMED CT terminology server. It also independently verifies a real upcoded diagnosis against the terminology graph, without another model call and with the same result on every run. The final verdict accuracy visibly improves, and the floor has never cleared a genuine defect; that counter is shown on every run. Everything shown runs against the live system with a per-run audit trail. The repo is public.

- Event context: AI Tinkerers Dubai — August Demo Day — 2026-08-08 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_e3czbFAtNPA

### [LMStack - Development stack using local LLMs](https://seattle.aitinkerers.org/talks/rsvp_A8GvI03RSK8)

Writing real code with local LLMs is difficult. lmstack is a local stack for real development which puts your GPU to work on the right kind of tasks. LMStack introduces an infrastructure manager and a task classifier. Both of them work together to make sure local models are always at work. I've been using this stack for a month to build features on an open source project - Clawrium. LMStack show why the entire stack needs to be different when using local llms and what're the pitfalls of using standard tooling. What works and what to avoid.

- Event context: AI Dev Tools Track - Seattle - August 4 — 2026-08-05 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_A8GvI03RSK8

### ["QA a la velocidad de la luz (y sin fuga de datos): potenciando testing exploratorio con modelos de IA ejecutados 100% en local](https://panama.aitinkerers.org/talks/rsvp_RO5JPx08rOc)

FullQA.ai es una plataforma de QA asistida por IA que genera, documenta y automatiza casos de prueba a partir de la exploración de una aplicación web, ejecutando los modelos de lenguaje y visión completamente en local — sin depender de APIs externas ni exponer datos sensibles. En la demo mostraré en vivo un flujo completo de punta a punta: El sistema funcionando en tiempo real: una extensión de navegador captura la sesión exploratoria (clics, navegación, formularios) y el backend la convierte en documentación de QA estructurada con capturas por paso. Arquitectura: cómo se conectan la extensión, la app de escritorio, el servicio API y los modelos locales servidos vía Ollama, con fallback a disco y generación de imágenes deterministas por paso. Generación de código: cómo se produce automáticamente un script de Playwright listo para ejecutar a partir de la sesión grabada. Repo y logs: enseñaré el código real, la estructura de proyectos con contexto, y los logs de inferencia local corriendo sobre la GPU.

- Event context: AI Tinkerers Panamá: Construyendo el futuro con inteligencia artificial — 2026-07-31 — Panama
- Public talk page: https://panama.aitinkerers.org/talks/rsvp_RO5JPx08rOc

### [Agent Memory Is the Softest Attack Surface. Let Me Show You.](https://minneapolis-saint-paul.aitinkerers.org/talks/rsvp_vxTZZYnTRxQ)

A memory-enabled AI financial advisor for small businesses that remembers each customer across sessions. The app is just the testbed. The real subject is agent-memory security: what breaks when you give an agent long-lived, multi-tenant memory. It runs on a real stack, with vector-searched long-term memory, per-tenant isolation, and live similarity scores on screen. In the demo I show it working, then run two live attacks on its memory: a cross-tenant data leak on the read path, and a persistent memory-poisoning injection on the write path. Then I show the defense for each. Everything is live: the working system, the memory recall panel, the one line of code that is the entire tenant boundary, and the toggles that break and fix it. No slides. Synthetic data only.

- Event context: AI Tinkerers Minneapolis-Saint Paul — July Meetup — 2026-07-29 — Minneapolis Saint Paul
- Public talk page: https://minneapolis-saint-paul.aitinkerers.org/talks/rsvp_vxTZZYnTRxQ

### [Wireless Intelligence](https://manizales.aitinkerers.org/talks/rsvp_5fU_jY0MJDY)

Wintelligence is a Python/Django web application designed to scan the local wireless spectrum, log nearby networks, and audit their security configurations. It flags weak configurations (such as WEP, Open networks, and legacy WPA) and displays results in an interactive, responsive web interface.

- Event context: 🚀 ¡18vo Encuentro de AI Tinkerers Manizales! 🤖 — 2026-07-28 — Manizales
- Public talk page: https://manizales.aitinkerers.org/talks/rsvp_5fU_jY0MJDY

### [AI as a Citizen's Governance Sidekick: Building a Practical Accountability Toolkit for Indiana Townships](https://fort-wayne.aitinkerers.org/talks/rsvp_lzBNfCu-WNk)

The Citizen Accountability Toolkit is a practical, citizen-led, AI-assisted guide that helps Indiana residents evaluate and strengthen local government performance in areas like public safety, transparency, and fiscal responsibility." In this demo, I'll showcase the real-world workflow we built: the 0-100 scoring system (with the Jackson Township fire services case study), the Live Interview Agent that turns meeting notes into scores, action trackers, one-page briefs, and APRA follow-ups, plus governance checklists. You'll see it live as I paste sample notes and instantly generate an updated score, brief, and next-step letter—demonstrating a human-controlled system that delivers immediately usable results for civic impact.

- Event context: AI Tinkerers Fort Wayne: July 2026 Meetup — 2026-07-25 — Fort Wayne
- Public talk page: https://fort-wayne.aitinkerers.org/talks/rsvp_lzBNfCu-WNk

### [Taskless: I Stopped Writing Tasks and Let My Notes Do It](https://islamabad-rawalpindi.aitinkerers.org/talks/rsvp_R83DVSpQNFA)

Taskless is a local automation that reads my raw, messy Obsidian thought-dumps and turns them into ClickUp tasks on its own, no manual task entry, no project-manager busywork. Live, I'll drop a real note dump into the watched vault and you'll watch n8n pick it up, the LLM classify each line as new / done / progress / ignore, and ClickUp create new tasks and close finished ones in real time from plain prose like "fixed the auth login bug today." I'll show the working n8n workflow, the LLM classification + dedup-by-hash steps, the execution logs as it runs, and the repo.

- Event context: AI Tinkerers Islamabad - July 18, 2026 — 2026-07-18 — Islamabad Rawalpindi
- Public talk page: https://islamabad-rawalpindi.aitinkerers.org/talks/rsvp_R83DVSpQNFA

## Related Technologies

- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [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
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 219 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Streamlit](https://aitinkerers.org/technologies/streamlit) ([Markdown](https://aitinkerers.org/technologies/streamlit.md)) — 89 public demos
- [Transformers](https://aitinkerers.org/technologies/transformers) ([Markdown](https://aitinkerers.org/technologies/transformers.md)) — 148 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 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
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 105 public demos
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [LangGraph](https://aitinkerers.org/technologies/langgraph) ([Markdown](https://aitinkerers.org/technologies/langgraph.md)) — 67 public demos
- [Ollama](https://aitinkerers.org/technologies/ollama) ([Markdown](https://aitinkerers.org/technologies/ollama.md)) — 77 public demos

## More Results

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