# Python Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/python?page=4
> Markdown URL: https://aitinkerers.org/technologies/python.md?page=4
> Technology record last updated: 2026-09-18T15:13:57Z
> Generated: 2026-09-22T15:44:38Z

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: 4 of 28

## Recent Public Talks and Demos

### [eomer: An Agentic Operating System for Data Science](https://singapore.aitinkerers.org/talks/rsvp_2G9vgEuwDJc)

eomer is an agentic operating system for data science that fine-tunes tabular foundation models on proprietary data to deliver production-ready forecasting, regression, and classification pipelines. In this demo, I’ll show how we go from raw enterprise data (CSV / DB) → automated feature handling → model selection & fine-tuning → calibrated forecasts with uncertainty → deployable outputs (API/UI) in a single workflow, without bespoke ML engineering.

- Event context: AI Tinkerers Singapore: The Agentic Future & Dev/Eng Workflows — 2026-04-21 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_2G9vgEuwDJc

### [Who Shipped What: Maintaining Codebase Context](https://singapore.aitinkerers.org/talks/rsvp_7b-BmRva9Ls)

Trajan is an always-on agent that maintains the real-time state of a codebase by continuously ingesting commits, pull requests, and repository structure, and turning them into up-to-date, queryable context. I’ll connect Trajan to a live repository, show how it reconstructs what shipped across contributors, generates and updates documentation automatically, and answers questions about the system using current state, without requiring manual prompts or periodic re-indexing.

- Event context: AI Tinkerers Singapore: The Agentic Future & Dev/Eng Workflows — 2026-04-21 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_7b-BmRva9Ls

### [Soul, Memory, Skills, Brain: Building a Zero-PII Personal AI Agent in Docker](https://austin.aitinkerers.org/talks/rsvp_11W1r8whPMs)

Rent-An-Agent.AI is a self-hostable personal AI agent platform where each agent is a four-layer artifact — Soul (persona in SOUL.md), Memory (SQLite+FTS5 with daemon-thread fact extraction), Skills (52 marketplace skills exposed through an OpenAI-compatible bridge API), and Brain (user-configurable LLM: DeepSeek, Ollama, Claude). It runs on a Mac Mini in Austin, ships as Docker containers on GitHub, exposes itself via Cloudflare Tunnel, and uses a 48-character hex token as the only identity — no email, no password, no PII. Live demo: provision a fresh agent in 10 seconds with persona picker, have a conversation, show the daemon thread silently extracting facts into SQLite, rewrite the Soul mid-conversation („Luna, sei ab jetzt formeller"), fire a marketplace skill call through the Bridge, and settle a tier upgrade with a real BOLT11 Lightning invoice via the Alby webhook.

- Event context: AI Tinkerers Austin: April 2026 Demo Night — 2026-04-16 — Austin
- Public talk page: https://austin.aitinkerers.org/talks/rsvp_11W1r8whPMs

### [Pista Inteligente: Cómo construí un sistema de ranking de carreras de caballos con LightGBM, Claude como extractor de datos y calibración isotónica](https://santiago.aitinkerers.org/talks/rsvp_EiElZqyICcA)

Construí Pista Inteligente, un pipeline de Machine Learning end-to-end que predice el orden de llegada de caballos en carreras del Club Hípico de Santiago e Hipódromo Chile. El sistema convierte programas de carreras en papel (PDFs y texto) en CSV estructurado usando prompts especializados con Claude. Esos datos alimentan un modelo LightGBM Ranker (LambdaRank) con Walk-Forward Validation que ordena los caballos por probabilidad de victoria. Las probabilidades crudas del modelo pasan por calibración isotónica para que los scores sean realmente interpretables como probabilidades. La arquitectura completa está en Python con mlflow para tracking de experimentos.

- Event context: 🔥 AI TINKERERS - SANTIAGO / CAPÍTULO #10 / 2026 — 2026-04-16 — Santiago
- Public talk page: https://santiago.aitinkerers.org/talks/rsvp_EiElZqyICcA

### [Stop the Confident BS: Reflective Retrieval Agents and Human-in-the-Loop Interrupts](https://cologne.aitinkerers.org/talks/rsvp_LyKSpKSeRVQ)

We built a reflective agent prototype that evaluates its own retrieved context and halts for human clarification before it hallucinates. In the live demo, we'll first break a standard one-prompt RAG setup to show how it confidently gives answers when faced with poorly defined context. Then, we will query our prototype, showcasing the live execution. You will see the agent evaluate its context, hit an uncertainty threshold, trigger a Human-in-the-Loop (HITL) interrupt to ask for missing parameters, and finally generate a factually grounded answer.

- Event context: AI Tinkerers Cologne 4: Live Technical Demos — 2026-04-16 — Cologne
- Public talk page: https://cologne.aitinkerers.org/talks/rsvp_LyKSpKSeRVQ

### [Wisdom Layer: Agent Cognitive Architecture](https://manchester-nh.aitinkerers.org/talks/rsvp_hAZ9fGsxhsI)

The Wisdom Layer is a Python SDK that wraps any LLM with persistent memory that matures, autonomous reflection cycles, self-authored behavioral rules with a lifecycle, and an internal critic that evaluates output against active rules before it ships. The demo at AI Tinkerers ran on Claude Haiku — Anthropic's cheapest model — and showed how a commodity model becomes substantially more reliable when scaffolded with memory, reflection, and enforcement, rather than fine-tuned. Early benchmark showed fabrication rate dropping from 22% to 2% on the same model (n=45 single corpus, broader eval in progress). The same architecture also powers loom-code (AI-assisted coding across 20+ repos) and a computational pharmacogenomics research platform in active collaboration discussions with academic cancer centers.

- Event context: AI Tinkerers Manchester (Bedford), NH - April 2026 Meetup — 2026-04-15 — Manchester NH
- Public talk page: https://manchester-nh.aitinkerers.org/talks/rsvp_hAZ9fGsxhsI

### [MoE parameters, MoE problems: visualizing Mixture of Experts Routing Layers](https://manchester-nh.aitinkerers.org/talks/rsvp_vIT84Fso8c4)

I built a real-time neural telemetry engine designed to intercept and visualize the internal gating decisions of a Mixture of Experts (MoE) model at a deeper level. The project utilizes a PyTorch forward hook to capture raw 40-dimensional routing weights from Layer 20 of an IBM Granite 3.0 model. By running this entirely on a laptop, the demo provides a live "neural heartbeat" that proves how sparse activation can achieve high-performance reasoning without the latency or computational waste of a cloud-scale cluster.

- Event context: AI Tinkerers Manchester (Bedford), NH - April 2026 Meetup — 2026-04-15 — Manchester NH
- Public talk page: https://manchester-nh.aitinkerers.org/talks/rsvp_vIT84Fso8c4

### [Training AI Like a Dog: What Behavioral Science Reveals About Model Alignment](https://chicago.aitinkerers.org/talks/rsvp_pdXZi3kLrDs)

A behavioral auditing and intervention system that runs alongside a language model in real time, detecting drift, entropy, and reward signal dysfunction while correcting for root cause rather than surface behavior. Built off-API on a local small model with no GPU using operant conditioning principles from high-stakes K9 training as the architectural foundation.

- Event context: AI Tinkerers Chicago: April Meetup ft OneTwoLoop — 2026-04-14 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_pdXZi3kLrDs

### [Autonomous background coding agents](https://houston.aitinkerers.org/talks/rsvp_oNQb0zIHFIE)

An implementation for an autonomous background coding agent to run long horizon tasks

- Event context: AI Tinkerers Houston: April Meetup — 2026-04-14 — Houston
- Public talk page: https://houston.aitinkerers.org/talks/rsvp_oNQb0zIHFIE

### ["From Noise to Signal: How a Team of AI Agents Turns Global Supply Chain Chaos into Actionable Intelligence"](https://st-louis.aitinkerers.org/talks/rsvp_EasqleNNKLg)

We built a supply chain intelligence platform that deploys a coordinated team of four AI agents to scan thousands of global news sources and instantly surface the events, risks, and patterns that matter most to traders, analysts, and executives. Demo context: Imagine you're a commodities trader. You need to know everything relevant about aluminum and tariffs — right now. Instead of spending 10 hours manually combing through 50+ news sources, you ask a single question. Within seconds, four AI agents divide the work: one decides which data domains to search, one plans the analysis strategy, one constructs precise database queries, and one synthesizes everything into a structured intelligence brief — complete with sources you can verify yourself.

- Event context: AI Tinkerers St. Louis: April 2026 Meetup — 2026-04-14 — St. Louis
- Public talk page: https://st-louis.aitinkerers.org/talks/rsvp_EasqleNNKLg

### [Computer Vision Pipeline for Drone Image Processing](https://st-louis.aitinkerers.org/talks/rsvp_yf6HEWzPJW4)

With Claude Code and GitHub SpecKit, I built a local web app which allows me to upload images, define regions of interest, and spin up a docker container to process images from my drone to do things like count cars. The container is CUDA aware and uses the GPU for faster processing. Single image processing takes about 30 seconds per image (super easy to demo quickly)

- Event context: AI Tinkerers St. Louis: April 2026 Meetup — 2026-04-14 — St. Louis
- Public talk page: https://st-louis.aitinkerers.org/talks/rsvp_yf6HEWzPJW4

### [Virtual model endpoints: fast mode, long context, & unlimited context](https://seattle.aitinkerers.org/talks/rsvp_jFDQjMA0UtY)

We optimize GPU compute for inference. We've stood up several clusters of capacity serving common/popular models. This has pushed us to providing unique variants that solve common context/memory issues and we've provided these in a way that's a simple as changing to another OpenAI compliant model. For development or agentic scenarios, these can enable multi-million context as well as unlimited model context all behind a simple model endpoint.

- Event context: AI Dev Tool Track — Seattle Meetup - April 13th, 2026 — 2026-04-14 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_jFDQjMA0UtY

### [Reverse-Engineering Video Editing Styles into Programmatic Templates via AI](https://dublin.aitinkerers.org/talks/rsvp_6EoN2x9ohBc)

I am building a feature for my video automation platform (shablon.co) that eliminates the manual toil of replicating complex video formats. Instead of manually adjusting cuts and keyframes, a user inputs a reference video. The system processes the file, analyzes the visual and auditory components (cut frequency, typography, motion graphics, transitions, and pacing), and extracts these parameters into a structured, programmatic template. It essentially reverse-engineers a final render back into a parameterized blueprint that can be instantly applied to fresh raw footage.

- Event context: AI Tinkerers Dublin Meetup — Baseline, April 9, 2026 — 2026-04-09 — Dublin
- Public talk page: https://dublin.aitinkerers.org/talks/rsvp_6EoN2x9ohBc

### [Ormah - A whispering proactive memory system for all your agents.](https://dublin.aitinkerers.org/talks/rsvp_iMDy7EdsIhc)

Ormah is the collective, self-maintaining memory layer all your agents can tap into. The core idea is simple: memory should be involuntary. Your agents should not have to remember to remember. Ormah works in the background, learning preferences, decisions, patterns, mistakes, and ongoing work, then whispering the right memory at the right time without your agent having to do anything. Your memory has always been yours. Ormah helps keep it that way. Local. Private. Portable. Yours to keep. Yours to move. www.ormah.me docs : - https://www.ormah.me/docs/how-ormah-works/overview - https://www.ormah.me/docs/getting-started/quickstart

- Event context: AI Tinkerers Dublin Meetup — Baseline, April 9, 2026 — 2026-04-09 — Dublin
- Public talk page: https://dublin.aitinkerers.org/talks/rsvp_iMDy7EdsIhc

### [Replacing Analysts in commodity trading](https://zurich.aitinkerers.org/talks/rsvp_i8MtV8raWAE)

Informatiom system built to deliver what traders want in LNG / Gas speculative decisions. - Visualize Fundamentals - Machine Learning models - Automate processes (anomalies alerts, analyze competitors, check auctions) - Data architecture automation - News embeddings and semantic analyzes (check what moves the market) - Monitoring users for automated feedback

- Event context: AI Tinkerers Zurich April 9th — 2026-04-09 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_i8MtV8raWAE

### [The Zero-Partners VC - AI Native VC running on AI Agents](https://zurich.aitinkerers.org/talks/rsvp_cPNM9rUu4j8)

We are www.ellipsis-venture.com - 2 GPs who are AI Builders (x-Google, x-founders, x-Apple) who run a fund without employees. We built an agentic system that runs everything - sourcing, due diligence, score cards and memos, marketing, Investors Relations, Ops, etc.

- Event context: AI Tinkerers Zurich April 9th — 2026-04-09 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_cPNM9rUu4j8

### [CyberRunner: How We Open-Sourced the AI That Beat Humans](https://zurich.aitinkerers.org/talks/rsvp_95B2B3fk6Sc)

CyberRunner is the first AI-driven robotic system to learn and master the physical "Labyrinth" marble game through reinforcement learning, achieving times that surpass the world record set by humans. This talk explores the transition from a laboratory experiment to a fully open-sourced hardware and software stack designed to democratize high-speed, high-precision robotic control.

- Event context: AI Tinkerers Zurich April 9th — 2026-04-09 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_95B2B3fk6Sc

### [Clawloop - the unified learning api](https://zurich.aitinkerers.org/talks/rsvp_sEFw1hfu1rc)

Clawloop is the learning from experience layer for AI agents. It turns traces, failures, and user feedback from production traffic and interactions with training environments into updates to an agent’s harness and weights. The harness includes prompt, memory, and tools, so Clawloop can improve not just the model but also how the agent is instructed and equipped. It plugs into stacks like LiteLLM, OpenClaw, and n8n and connects to training backends like SkyRL and Tinker for weight adaptation.

- Event context: AI Tinkerers Zurich April 9th — 2026-04-09 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_sEFw1hfu1rc

### [From 1 Agent to 11: Patterns for Multi-Agent Systems That Actually Work](https://columbus.aitinkerers.org/talks/rsvp_nZaEJ2xzX0c)

I built an AI operating system (AIOS) that runs my technology community organization, Cloud Nirvana, using 11 specialized AI agents coordinated from a Mac Mini. Each agent owns a domain: email triage, speaker pipeline QA, partnership tracking, CRM operations, content, community engagement, financial operations, and strategic planning. They share an encrypted CRM, communicate through file-based memory, and operate under a graduated trust model where each agent earns autonomy based on demonstrated reliability. Along the way, everything broke at least once. I documented those failures as reusable engineering patterns (inspired by the Gang of Four) and open-sourced them. The demo walks through the live system, shows agents handling real work in real time, and demonstrates how any builder can discover and apply these patterns against their own codebase.

- Event context: AI Tinkerers - Columbus April Meetup — 2026-04-06 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_nZaEJ2xzX0c

### [Reverse Ralph Loops](https://columbus.aitinkerers.org/talks/rsvp_GkXWwT0FF3A)

I built an app that runs a reverse Ralph Wiggum loop over an existing codebases to create a clean room specification of features or whole applications. You can then use these specifications to recreate the software for yourself. I wanted a deep research tool for my coding agents. So I looked at the leaderboard for deep research agents and picked the top open source project. I then ran an LLM in a loop to work on one aspect of the specification on each iteration until the full specification was created for the deep research functionality. I then used the specification with a loop that handled one implementation task from the spec on each iteration to create my own deep research CLI.

- Event context: AI Tinkerers - Columbus April Meetup — 2026-04-06 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_GkXWwT0FF3A

### [Nanochat: training your own LLM chat bot from scratch](https://belgium.aitinkerers.org/talks/rsvp_dBCcFb9t3nk)

I'll walk the audience through Andrej Karpathy's latest reincarnation of minGPT/nanogpt, namely nanochat. This repo contains all major LLM stages including tokenization, pretraining, finetuning, evaluation, inference, and even a chat UI. Its minimalistic implementation allows you to train and evaluate an LLM from scratch, on a single GPU node or even a CPU. With access to better GPU machines (e.g. an 8X H100), you can get up to GPT2-level performance in under 2 hours!

- Event context: AI Tinkerers Antwerp Meetup - April 1 (no joke) — 2026-04-01 — Belgium
- Public talk page: https://belgium.aitinkerers.org/talks/rsvp_dBCcFb9t3nk

### [Agentic Trust in the Age of Dangerously Skipping Permissions](https://boston.aitinkerers.org/talks/rsvp_6lNq1OMTLsA)

Agentic Trust and Verification system mvp/poc that showcases the attack surface that agentic tools are creating on our computers and in our world.

- Event context: AI Tinkerers Boston: March 2026 Meetup — 2026-03-30 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_6lNq1OMTLsA

### [Graph-Enhanced XGBoost: Beating Fraud Detection Baselines with Neo4j](https://saopaulo.aitinkerers.org/talks/rsvp_jIeBaJ1l7t8)

A graph-based financial fraud detection system built on Neo4j, using the IEEE-CIS dataset to model transactions, cards, devices, emails, and addresses as a connected network — and combining graph features with XGBoost to significantly outperform traditional tabular models.

- Event context: AI Tinkerers SP e Banco BMG — 2026-03-26 — São Paulo
- Public talk page: https://saopaulo.aitinkerers.org/talks/rsvp_jIeBaJ1l7t8

### [Sales Data Driven AI](https://saopaulo.aitinkerers.org/talks/rsvp_TIZxQLTfXv0)

Um sistema de vendas automático e dando direcionamento baseado em dados conversacionais da IA com o lead.

- Event context: AI Tinkerers SP e Banco BMG — 2026-03-26 — São Paulo
- Public talk page: https://saopaulo.aitinkerers.org/talks/rsvp_TIZxQLTfXv0

## 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)) — 220 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)) — 216 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 174 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 106 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

- Previous: https://aitinkerers.org/technologies/python.md?page=3
- Next: https://aitinkerers.org/technologies/python.md?page=5