# Python Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/python?page=3
> Markdown URL: https://aitinkerers.org/technologies/python.md?page=3
> Technology record last updated: 2026-09-18T15:13:57Z
> Generated: 2026-09-20T20:36:25Z

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: 3 of 28

## Recent Public Talks and Demos

### [Talking to Your Infrastructure: Building a Conversational DevOps Agent with Rasa](https://paris.aitinkerers.org/talks/rsvp_IjdWIc5gQv4)

In this talk, I’ll share how I built a conversational AI agent using Rasa and the Scalingo API to manage real applications through natural language. Create apps, scale services, check logs, or update environment variables all with a single sentence. If infrastructure became conversational, what you will told her?

- Event context: AI Tinkerers Paris feat Scalingo: Conversational DevOps & AI Infrastructure — 2026-05-21 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_IjdWIc5gQv4

### [JEN-R8 Discovery Engine: An AI That Tries to Prove Itself Wrong](https://manchester-nh.aitinkerers.org/talks/rsvp_1xgFaiUwGiA)

JEN-R8 is an AI research engine that tries to prove itself wrong. It synthesizes hypotheses across scientific domains, pre-registers the exact conditions under which it will declare itself defeated, runs the analysis on public data, and auto-generates a post-mortem when its own gates fail. Those post-mortems then feed back into the next round of hypothesis generation; the engine learns from its own failures. You'll see the full loop live: cross-domain bridge -> drafted hypothesis spec -> pre-registered falsification gates -> real-time execution on public data -> a meaningful failure -> the engine articulating, on stage, exactly why its own claim was wrong. Then I'll walk through the operator console. Current state (as of demo time): - 60 hypotheses across 15 scientific domains - 5 hypotheses confirmed through full gate passage - 6 hypotheses abandoned with documented post-mortems - 5 provisional patents filed in cancer biomarker discovery - 3 pre-print papers in preparation - 2 developing collaborations with university research institutes JEN-R8 was designed and built by agents running on the Wisdom Layer SDK (the subject of my AI Tinkerers demo last month, featured in the April global newsletter.)

- Event context: AI Tinkerers Manchester (Bedford), NH - May 2026 Meetup — 2026-05-20 — Manchester NH
- Public talk page: https://manchester-nh.aitinkerers.org/talks/rsvp_1xgFaiUwGiA

### [Towards Embodied AI with MuscleMimic: Unlocking full-body musculoskeletal motor learning at scale](https://geneva.aitinkerers.org/talks/rsvp__HfRwdkJpVI)

MuscleMimic is an open-source, JAX-based framework for scalable motion imitation learning with physiologically realistic muscle-actuated humanoids. It provides validated musculoskeletal embodiments, including a 126-muscle upper-body model for bimanual manipulation and a 416-muscle full-body model for locomotion, together with motion-retargeting pipelines, pretrained checkpoints, datasets, and GPU-parallel training tools for learning human-like movement under full muscular control. By lowering the computational barrier to biomechanically accurate motor learning, MuscleMimic enables research at the intersection of embodied AI, reinforcement learning, biomechanics, neuroscience, robotics, and human movement science. Repo: https://github.com/amathislab/musclemimic Hugging Face playground: https://huggingface.co/spaces/amathislab/musclemimic_space

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

### [Reducing eWaste with AI: how old devices can be brought back to life](https://raleigh.aitinkerers.org/talks/rsvp_8BhOnI30T4E)

I had an old audio device that hasn’t had working drivers for years on macOS that ai helped me bring back to life. The process required reverse engineering the last working driver version, and arguing with the ai about it the entire time. I was able to observe the ai preferred working in assembly and we can look at some reasons why this may or may not be a good thing.

- Event context: AI Tinkerers Raleigh Meetup — May 6, 2026 — 2026-05-06 — Raleigh
- Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_8BhOnI30T4E

### [Patent Mining for Engineers: Building an Agentic RAG System for Inventive Problem Solving using TRIZ & AI](https://poland.aitinkerers.org/talks/rsvp_oYsjqZvaY7E)

A pipeline that parses patent PDFs, extracts Technical Contradictions, classifies solutions into TRIZ Inventive Principles, and indexes everything into a vector database. This collection is then feeding an AI Agent that helps engineers solve real inventive problems. The demo starts with a raw patent PDF, submits it live to the processing endpoint, and walks through what gets extracted and indexed. Then, given a real mechanical engineering problem, the agent frames it as a TRIZ contradiction, retrieves relevant patents, and proposes concrete solution ideas, powered by domain knowledge, not just plain LLM generation.

- Event context: AI Tinkerers Poland #3 - Meetup in Wrocław — 2026-05-06 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_oYsjqZvaY7E

### [AI Launcher for old games on Mac OS (very millennial / boomer)](https://seattle.aitinkerers.org/talks/rsvp_jmXoHb_fAoc)

Cellar is AI pipeline based on Wine with the only goal – to launch an old games on your Mac. Launching old games on Mac is especially notorious business based on reading manuals, tweaking configs and it is not fun (at least for me). To help nostalgic newbies as I am, I made this tool – Cellar. It is a bundle of Wine and AI pipeline. You point it to the installation file and does everything for you: unpacks it, installs, creates a bottle and finds correct configuration to launch. Once the game is launched, successful config stored and you don't need AI anymore. Additionally, all Cellar agents have shared Wiki that collects all their experiences together – so that if one Cellar agent launched game correctly, another one will read about it. It currently supports Claude, Deepseek and Kimi.

- Event context: AI Dev Tools Track - Seattle — 2026-05-06 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_jmXoHb_fAoc

### [Porting Segment Anything: SAM2 in ONNX/C++, SAM3 in thin scripts](https://lausanne.aitinkerers.org/talks/rsvp_HLLk1mziQvk)

I built a portable interactive segmentation stack around Segment Anything: a C++/ONNX Runtime wrapper for SAM2 plus thin SAM3 image/video demo scripts that run on Windows CUDA or macOS Apple Silicon. In the demo I’ll show prompt-driven segmentation and video propagation, then pop the hood on how I split the model/runtime pieces so the same workflow runs outside research notebooks.

- Event context: AI Tinkerers Lausanne April 2026 Meetup — 2026-04-30 — Lausanne
- Public talk page: https://lausanne.aitinkerers.org/talks/rsvp_HLLk1mziQvk

### [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

### [Watch a Sales Guy Ship Agentic Infrastructure](https://toronto.aitinkerers.org/talks/rsvp_UMP1pQfK9Bo)

Human commerce runs on trust. Agentic commerce will run on confidence. Disclose Framework is an open standard for publishing the operational signals autonomous systems need to evaluate businesses with confidence. This demo will focus on commerce. It shows an MCP server that reads a merchant's /.well-known/disclose file and returns structured operational data, including return rate, fulfillment accuracy, and chargeback ratio, so an agent can evaluate a seller on verifiable facts rather than reviews or price alone.

- Event context: AI Tinkerers Toronto - April 2026 - hosted by Shopify — 2026-04-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_UMP1pQfK9Bo

### [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

### [Bugtrace AI: Building the First Deterministic Agentic Framework for Reliable Web Pentesting](https://hong-kong.aitinkerers.org/talks/rsvp_pv9QZncWqV0)

Bugtrace AI is the first deterministic Agentic AI framework specifically engineered for automated web pentesting.

- Event context: AI Tinkerers Hong Kong at AWS: Agentic AI in Action (April) — 2026-04-29 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_pv9QZncWqV0

### [Sarathy & me!](https://ottawa.aitinkerers.org/talks/rsvp_bcfMBtYyxgc)

A openclaw style personal assistant forked from nanobot, inspired from Hermes and openclaw

- Event context: AI Tinkerers Ottawa Meetup — April 25th, 2026 — 2026-04-25 — Ottawa
- Public talk page: https://ottawa.aitinkerers.org/talks/rsvp_bcfMBtYyxgc

### [Eric Chat: Run AI models locally, securly and offline on Macs](https://ottawa.aitinkerers.org/talks/rsvp_3gOvbv-b9DU)

Eric Chat is a Python package that lets users run models up to 120 billion parameters offline on Macs with Apple Silicon. It provides an easy-to-use graphical user interface.

- Event context: AI Tinkerers Ottawa Meetup — April 25th, 2026 — 2026-04-25 — Ottawa
- Public talk page: https://ottawa.aitinkerers.org/talks/rsvp_3gOvbv-b9DU

### [Por qué los LLMs le fallan a tu tía — y el middleware que lo arregla](https://bogota.aitinkerers.org/talks/rsvp_IpWjE18ZKrY)

Un agente en OpenClaw/Python para adultos mayores con baja literacidad digital, accesible por WhatsApp/Telegram. Lo presenté en el hackathon de Tribu IA el 13 de abril con fallas graves. Esta demo muestra el diagnóstico, las tres correcciones de arquitectura, y los resultados de una sesión de prueba real con dos usuarias de +85 años.

- Event context: AI Tinkerers Bogotá: Demos for builders — 2026-04-23 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_IpWjE18ZKrY

### [Agentic AI for Engineering Data Analysis](https://karlsruhe.aitinkerers.org/talks/rsvp_6navkmqO9Ss)

Our Onion project is an agentic AI system that helps mechanical engineers to analyse test-, fleet- and production data. In the demo I'll introduce the use case and its requirements. I'll also show some key components for the system: Data infrastructure to handle sensor data efficiently, how to shape context in the AI harness, role of UI/UX for engineers.

- Event context: AI Tinkerers Karlsruhe: April Build Night — 2026-04-23 — Karlsruhe
- Public talk page: https://karlsruhe.aitinkerers.org/talks/rsvp_6navkmqO9Ss

### [MakoraGenerate - AI Agent for Optimizing GPU Code](https://poland.aitinkerers.org/talks/rsvp_bSNP53ASxRc)

MakoraGenerate writes highly performant GPU kernels, low-level code that is the backbone of modern AI compute infrastructure.

- Event context: AI Tinkerers Poland - Meetup in Gdańsk #1 — 2026-04-23 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_bSNP53ASxRc

### [Scaling RAG: Hybrid Search and Hierarchical Chunking for 780k Pages](https://poland.aitinkerers.org/talks/rsvp_BCaEvuBCHLM)

I built a custom desktop-server search engine designed to help me instantly find and manage documents within my 40GB PDF library. Technical Overview: - The Interface: A Windows application where I can search and browse through the results easily. - The Search Brain: A backend powered by FastAPI that uses "hybrid search" - Data Processing: Python and Bash scripts that handle the heavy lifting, such as pulling Markdown and generating page thumbnails from every file. - Annotation AI: vLLM based LLM server that extract metadata. - The Future: I am currently adding a RAG (Retrieval-Augmented Generation) feature so I can ask the AI questions directly about the content of my documents.

- Event context: AI Tinkerers Poland - Meetup in Gdańsk #1 — 2026-04-23 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_BCaEvuBCHLM

### [Self-serve Ray clusters for researchers who dislike kubernetes YAML](https://montreal.aitinkerers.org/talks/rsvp_CL9_5lbPlTc)

Krayne, a lightweight CLI, Python SDK, and interactive TUI (ikrayne) that provisions self-serve Ray clusters for AI researchers who dislike wrestling with Kubernetes manifests. For the demo, I will show how to bypass K8s YAML entirely to instantly bootstrap a Ray cluster using a simple command (krayne create) or through our interactive terminal interface (ikrayne). Then, I'll peek under the hood to show the actual technical implementation: how the tool translates these simple inputs into the complex KubeRay Custom Resources and API calls required to orchestrate the pods behind the scenes.

- Event context: AI Tinkerers Montreal - April Demo Night — 2026-04-22 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_CL9_5lbPlTc

### [Hive Mind vs Solo Agent: A Live Race to See If Multi-Agent Coordination Actually Beats Working Alone](https://montreal.aitinkerers.org/talks/rsvp_ytH2ELCp8bo)

A live head-to-head race pitting a single Claude Code agent against a ruflo Hive Mind, a "Tactical Queen" coordinating 4 specialized workers (architect, coder, tester, reviewer), both solving the same Python coding challenge in real time. The challenge is to build a sliding window rate limiter from scratch, including implementation, tests, and 80%+ coverage. A custom real-time scoreboard dashboard (Node.js + SSE) watches both workspaces simultaneously, streaming logs and tracking progress as files appear, tests run, and coverage is measured. When both sides finish, an automated evaluation scores them on a 100-point rubric (implementation, test pass rate, coverage, edge cases, time). It's a controlled experiment to answer the question: does multi-agent swarm coordination actually produce better code faster than a single focused agent?

- Event context: AI Tinkerers Montreal - April Demo Night — 2026-04-22 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_ytH2ELCp8bo

### [predict-rlm: Harness-less Recursive Language Models Built on DSPy](https://montreal.aitinkerers.org/talks/rsvp_xSr_Hb9LQQw)

predict-rlm is a callable RLM (Recursive Language Model) runtime built on top of DSPy. You define your inputs, outputs, and tools — the model handles its own control flow via a sandboxed REPL. I'll demo how it processes documents (PDFs, images, invoices) end-to-end, showing how a single RLM call can recursively decompose complex tasks into sub-LM calls — with fully interpretable trajectories and structured outputs — all without context rot.

- Event context: AI Tinkerers Montreal - April Demo Night — 2026-04-22 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_xSr_Hb9LQQw

### [ThreadHop: local-first context sharing across coding agent sessions](https://montreal.aitinkerers.org/talks/rsvp_72wf-elK3uc)

ThreadHop is a local TUI and CLI app that turns isolated coding-agent sessions into a connected workspace with a chat history view, cross-session Full Text Search (FTS5), a kanban board for session tagging, automatically extracted decisions and TODOs, bookmarks, and compressed handoffs. In this demo, I want to show how conversation history can be reused instead of ignored. ThreadHop indexes local transcripts, lets you organize chats on a kanban board with simple states like backlog, in progress, in review, and done, and makes it easy to bring the right context into a new session — whether that is a bookmarked turn, the open TODOs and decisions a background observer has already pulled out, or a full handoff through the /threadhop:handoff skill that packages decisions, TODOs, ADRs, and cross-session conflicts so work can carry forward. The goal is to make multi-agent coding feel like one continuous workspace rather than a pile of disconnected chats.

- Event context: AI Tinkerers Montreal - April Demo Night — 2026-04-22 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_72wf-elK3uc

### [Juggle 10+ projects in parallel without getting overwhelmed](https://atlanta.aitinkerers.org/talks/rsvp_chajEf1PUyg)

I am building what Claude described to be a Project Awareness System. As a developer I can now trust Claude to let me plan with it then have it write the code, but that leads to a lot of wait time. So I started working on multiple projects in parallel, each in a different tmux window so I don't end up having to wait. However, one project often begets often projects that it depends, so over time I found myself with over 15 parallel projects all in-progress. And with this I got lost in what to do next, and so did Claude. To address this I started building a web dashboard of all my current projects that gets its data from monitors running in hooks, on prompts and as a daemon. I call this software Endless. It is still very early and very much a work in progress.

- Event context: AI Tinkerers Atlanta: Community Demos & Technical Deep Dives — 2026-04-21 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_chajEf1PUyg

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

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

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

### [On-premise AI solution for Cloud PBX provider](https://valencia.aitinkerers.org/talks/rsvp_zguJ0GbdGVs)

On-premise AI transcription. I rebuild faster-whisper lib to make it more efficient for dual-channel transcription. I've built GPU-servers infrastructure for CloudPBX providers with transcirption and analysys.

- Event context: AI Tinkerers Valencia April Meetup — 2026-04-21 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_zguJ0GbdGVs

## 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

- Previous: https://aitinkerers.org/technologies/python.md?page=2
- Next: https://aitinkerers.org/technologies/python.md?page=4