# GitHub Actions Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/github-actions
> Markdown URL: https://aitinkerers.org/technologies/github-actions.md
> Technology record last updated: 2026-02-24T17:02:45Z
> Generated: 2026-08-26T06:20:56Z

GitHub Actions automates your software workflows (CI/CD, testing, deployment) directly within your repository.

GitHub Actions is your native, event-driven automation platform: it executes custom workflows right inside your GitHub repository. Define multi-step jobs using YAML files, which must be stored in the `.github/workflows` directory. These workflows trigger on specific events, like a `push` to a branch or a `pull_request` opening. The platform supports world-class Continuous Integration and Continuous Deployment (CI/CD), letting you build, test, and deploy code across any language (e.g., Python, Node.js, Java). Runners—Linux, Windows, or macOS virtual machines—execute the jobs. For security, confidential data is managed via GitHub `secrets`, ensuring credentials stay out of your code.

- Official technology site: https://github.com/features/actions
- Public AI Tinkerers demos and talks: 18
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Agents write the code, phones approve the merge: device-in-the-loop CI for AI-built mobile apps](https://seattle.aitinkerers.org/talks/rsvp_RZQnTBW084M)

An AI-assisted delivery workflow where coding agents ship mobile apps and physical phones give the final approval. A GitHub issue gets claimed by a Claude Code agent running in a long-lived tmux loop. The agent opens a PR with tests. CI on a self-hosted runner then installs the build on a real Pixel and a Wear OS watch through custom MCP device-control servers, runs the acceptance check, and posts device screenshots back to the PR. Live: the loop end to end on real hardware, MCP tool-call traces, the CI wiring, and the watchdog code that keeps a multi-day agent loop alive. Prerecorded backup for the device segment in case venue wifi dies.

- Event context: AI Dev Tools Track - Seattle - August 4 — 2026-08-05 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_RZQnTBW084M

### [Live/Real-Time Production Feature Implementation and Launch to Prod](https://minneapolis-saint-paul.aitinkerers.org/talks/rsvp_pLpxfavq3ik)

I'd like to do a live demo of me implementing a real feature on one of me products including spec, coding, CI/CD with launch to prod in real-time. Two products I'm actively developing right now: https://bartbot.mosaicmeshai.com/ https://transitionrowing.mosaicmeshai.com/ and either one is a good candidate for this live demo of my development process. I can come with a few ready to go ideas for these projects an the group can vote on which one they want me to implement, validate, test, and deploy during the demo.

- 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_pLpxfavq3ik

### [Accurate vibe analytics](https://nashville.aitinkerers.org/talks/rsvp_TEGj2gbUeIQ)

Dbt-skillz is a project I open sourced that "compiles" a dbt project into a claude code compatible skill. We use it in our CI/CD workflow to always stay fresh. We use it to (1) build accurate BI/reporting dashboards, and (2) review them with a review-agent workflow that uses the skill.

- Event context: AI Tinkerers Nashville – Software Development in the Age of AI — 2026-03-25 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_TEGj2gbUeIQ

### [Eliminating Waste in the AI Augmented SDLC](https://nashville.aitinkerers.org/talks/rsvp_uMKhslYmRfU)

When AI can use the same tools you use - Jira, GitHub, Sentry - the bottleneck in software development shifts from writing code to everything around the code. I applied lean manufacturing principles (Toyota Production System) to my own AI-augmented workflow and systematically removed entire categories of waste: manual ticket management, error triage, deployment monitoring, and ambiguous specifications that lead to expensive rework. I’ll walk through the specific patterns - MCP tool handoff, Gherkin specs as agent contracts, pre-flight checklists derived from PR review audits - and show how each elimination is permanent and reveals the next layer.

- Event context: AI Tinkerers Nashville – Software Development in the Age of AI — 2026-03-25 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_uMKhslYmRfU

### [rm -rf salesforce — Claude Runs Deal Flow Now](https://seattle.aitinkerers.org/talks/rsvp_qa7m-04lrlg)

I built a git-backed knowledge base that replaces both my CRM and Google Docs for running an early-stage fund. Every entity — founders, companies, deals — lives as a folder of markdown and YAML. Claude agents are first-class participants: they process inbound emails, run entity resolution, create records, log notes, and commit directly to the repo. A GitHub Actions cron runs nightly, calling Claude Sonnet to synthesize each entity's raw files into a structured materialized summary. I'll demo the full live workflow: forward a pitch email → agent resolves the entity → creates the records → generates a materialized view → commits to git. No database. No SaaS. Just files, Claude, and git.

- Event context: AI Tinkerers Seattle: GTM Engineering Kickoff — Building AI for Growth — 2026-02-26 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_qa7m-04lrlg

### [AI Job Agent: Automating Job Search with GitHub Actions, Vertex AI, and Strategic Laziness](https://atlanta.aitinkerers.org/talks/rsvp_MAVH3VnIET0)

I built an AI agent that autonomously searches LinkedIn, Indeed, and Greenhouse every Tuesday and Thursday, analyzes 40+ jobs using Vertex AI, and emails me a prioritized list with match scores and custom talking points—all while I sleep. The entire system runs serverless on GitHub Actions (completely free) and took two weekends to build.

- Event context: AI Tinkerers Atlanta: Code-First Demos & Technical Deep Dives | January 27, 2026 — 2026-01-27 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_MAVH3VnIET0

### [Aysnc AI Coding](https://atlanta.aitinkerers.org/talks/rsvp_nedDEigaRKQ)

AI coding demo, invoking Claude Code via GitHub Actions, and the CI/CD that makes it useful

- Event context: Co-Co-Code & Cocoa: The AI Tinkerers Atlanta Holiday Meetup — 2025-12-16 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_nedDEigaRKQ

### [AI driven events calendar for Cambridge](https://boston.aitinkerers.org/talks/rsvp_kNR147gJkOs)

Cambridge Day, a local newspaper, pays a contractor to scrape local websites and create a list of events for the upcoming week in Cambridge (https://www.cambridgeday.com/2025/11/27/a-week-of-events-in-cambridge-and-somerville-with-david-boobie-a-tea-lounge-and-film-turkeys/). This is a meaningful weekly cost for a cash strapped local nonprofit. I decided to build an automated events calendar with custom web scrapers with a much cleaner UI.

- Event context: AI Tinkerers Boston Meetup December 2025 — 2025-12-02 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_kNR147gJkOs

### [How I found vulnerabilities in MCP servers and fixed them!](https://seattle.aitinkerers.org/talks/rsvp_NFFtFla3aDY)

Demo showing how to create secure, standardized MCP servers from APIs, then connect an automated MCP scanner to GitHub that produces a security score, lists probe failures, and enables rapid investigation and remediation. This enables developers to ship MCP servers fast and secure in minutes.

- Event context: Trust & Security in AI: Demo Night w/ Auth0 — 2025-10-30 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_NFFtFla3aDY

### [Agentify Agent: Converting Pre-Built Agents into the Agentuity Framework](https://miami.aitinkerers.org/talks/rsvp_uJjSEJ3mvzw)

The Agentify Agent is an agent built on Agentuity that takes links to open-source AI agent examples (like CrewAI or Mastra) and automatically converts them into runnable Agentuity agents. It analyzes docs, extracts runnable TypeScript snippets, sets up the correct folder structure, and opens a pull request with a ready-to-run example. I’ll walk through how the agent interacts with Devin (the AI software engineer), how the prompt architecture was designed, and what we learned about agent onboarding.

- Event context: AI Tinkerers Miami Meetup — Fall Demo Night at The Lab — 2025-10-28 — Miami
- Public talk page: https://miami.aitinkerers.org/talks/rsvp_uJjSEJ3mvzw

### [Automating low-effort tickets with Linear, Claude Code and GitHub Actions](https://sf.aitinkerers.org/talks/rsvp_6du-tKfL8d0)

I'll be presenting a working demo of how we ship low-effort tickets from our Linear board using a research/plan/implement workflow built with GitHub actions, Claude Code, and linear. It's kind of like Devin but with better opinions about software development workflows and built-in context engineering best practices

- Event context: Agents in Production: Human in the Loop Orchestration w/ Temporal — 2025-10-17 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_6du-tKfL8d0

### [AI-B2in: AI-Powered In-Betweens for Real Animations](https://manizales.aitinkerers.org/talks/rsvp_IXAK25Tzaq8)

I will present AI-B2in, an AI tool designed to generate smooth in-betweens for real drawings and animations. Unlike generic interpolation systems, AI-B2in focuses on preserving artistic style while creating fluid motion. The demo will cover the full technical pipeline: image preprocessing, AI-driven frame interpolation, post-processing cleanup (binarization, line sharpening, blur reduction), and integration with modern web technologies. I will show live code and outputs from real animation samp

- Event context: 🚀 ¡Octavo Encuentro de AI Tinkerers Manizales! — 2025-09-24 — Manizales
- Public talk page: https://manizales.aitinkerers.org/talks/rsvp_IXAK25Tzaq8

### [PromptBud – Your Prompt Co-Pilot for Smarter AI Interactions](https://boston.aitinkerers.org/talks/rsvp_7KSMWEH0sYk)

In this talk, I’ll showcase PromptBud, a Chrome extension designed to elevate the way users interact with large language models. PromptBud acts as an intelligent co-pilot, scoring prompts in real-time, detecting PII automatically, offering optimized rewrites, and remembering recent context for better continuity. I will dive into how PromptBud integrates seamlessly with platforms like ChatGPT and Claude to help users—from beginners to advanced AI practitioners—craft more effective and secure prompts. Whether you're exploring creative writing, research, coding, or enterprise use cases, PromptBud helps users make the most of their AI tools with minimal friction.

- Event context: AI Tinkerers Boston June Meetup @ MIT! — 2025-06-30 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_7KSMWEH0sYk

### [Two Dice One Shake (QED): A 100 % Quantum-Safe Dual-KEM Protocol for Sub-5 ms Data Transfer](https://singapore.aitinkerers.org/talks/rsvp_52iUZMKf_DI)

Classical TLS will be broken the day practical quantum computers arrive. That threatens not just log-ins and banking but AI inference streams—the gRPC/HTTP pipes that move embeddings, model weights, or user prompts across GPU clusters. “Two Dice One Shake” (TDOS) is a drop-in, production-ready fix: a dual-KEM handshake that fuses Kyber-1024 key exchange with Dilithium-3 signatures to deliver 100 % quantum-safe encryption over plain HTTP/1.1—no TLS termination, no service-mesh surgery. In this live demo I’ll peel TDOS apart from the ground up: 1. Protocol Design – why rolling two independent KEMs (“the dice”) removes any single quantum-break point. 2. Implementation – Rust + OpenQuantumSafe bindings, compile-time guards that reject anything but NIST-exact key sizes, zero simulation fallbacks. 3. Performance – dual handshake in ≈ 4 ms, encrypted inference frames in < 1 ms; how async/await + zero-copy buffers keep your transformer payloads at line rate. 4. Verification Pipeline – a 10-stage CI suite that mathematically proves real PQC, hammers 100 + consecutive ops, and auto-fails on weak-crypto fall-backs. 5. AI-First Integration Paths – Axum/Tower middle-wares for Rust inference servers, Warp filters for fine-grained route control, plus Docker/K8s manifests so you can wrap a running model without touching your load-balancer. We’ll finish by routing a live embedding stream through TDOS, Wireshark-sniffing 1568-byte Kyber packets, and showing how to bolt the state machine onto an ONNX-runtime micro-service in < 20 LOC. Attendees leave with a reproducibility script, a working Axum demo, and a mental model for shipping quantum-safe AI APIs today, not “when NIST finalises.”

- Event context: AI Tinkerers Singapore: 8th Meetup - Antler x Sambanova - June 20th, 2025 — 2025-06-20 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_52iUZMKf_DI

### [Agent testing with transactions](https://seattle.aitinkerers.org/talks/rsvp_l7Lv36QkvdA)

As the agent logic and graph becomes more complicated, the need of establish a stable baseline to iteratively add capabilities and improve quality of agents is critical to those who are like us at Otto building AI agent to do transactions. We take a similar approach as the one proposed in the τ -bench in this paper (https://arxiv.org/pdf/2406.12045) that’s probabilistic oriented rather than deterministic oriented, yet focusing on testing our own scenarios rather than a benchmark of general capability. Would like to share some early learnings and thoughts around stability, setup and point of testing after testing a handful of choices (Pytest vs Puppeteer/Selenium, Github Action vs CircleCI vs Azure DevOps, end-to-end testing vs langGraph node testing).

- Event context: AI Tinkerers Seattle - December 2024 Meetup — 2024-12-12 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_l7Lv36QkvdA

### [Off Topic Guardrails / Automation with LLMs & GitHub Actions](https://singapore.aitinkerers.org/talks/rsvp_PsNuftEsdZU)

I’m deciding between the two Ideal 1: Finetuning embedding models to classify if a user prompt is on/off topic with reference to a system prompt. I Will quick demo synthetic data generation process, architecture, and model Idea 2: Here, I demo a simple repo that summarises arVix papers with Gemini’s pdf processing & GitHub actions. The pipeline automatically updates the README daily.

- Event context: AI Tinkerers Singapore: Meetup - September 16th, 2024 — 2024-09-16 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_PsNuftEsdZU

### [Orchestrating GPTs with Haystack 2.0: Easily Build Cool NLP Apps Like Auto PR and Auto Reno](https://berlin.aitinkerers.org/talks/rsvp_H7-4fDwAVIA)

Join us to discover how Haystack 2.0 transforms the orchestration of GPTs, making it simpler than ever to develop your own NLP applications. In this session, we'll not only demonstrate GitHub Actions: Auto PR and Auto Reno, but also show how Haystack 2.0 enables NLP/AI enthusiasts to create complex apps effortlessly. We aim to demystify the process of NLP app development, showing how anyone can leverage advanced LLMs to build both practical and captivating applications.

- Event context: AI Tinkerers Berlin - March 21 — 2024-03-21 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_H7-4fDwAVIA

### [Q&A Chatbot (Langfuse Docs)](https://berlin.aitinkerers.org/talks/rsvp_ziwzF7Fao8I)

Q&A chatbot that I've built for the Langfuse docs using pgvector, edge functions, GH actions embedding pipeline for mdx documentation, Openai streaming, the Vercel AI SDK, shadcn frontend components, and Langfuse (open-source analytics to understand what does not work and how to improve it).

- Event context: AI Tinkerers Berlin - November 24 — 2023-11-24 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_ziwzF7Fao8I

## Related Technologies

- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 205 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 654 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 187 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 123 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 199 public demos
- [CI/CD](https://aitinkerers.org/technologies/ci-cd) ([Markdown](https://aitinkerers.org/technologies/ci-cd.md)) — 7 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 144 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 518 public demos
- [Agentuity SDK](https://aitinkerers.org/technologies/agentuity-sdk) ([Markdown](https://aitinkerers.org/technologies/agentuity-sdk.md)) — 1 public demo
- [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 63 public demos
- [arXiv](https://aitinkerers.org/technologies/arxiv) ([Markdown](https://aitinkerers.org/technologies/arxiv.md)) — 8 public demos
- [Auto PR](https://aitinkerers.org/technologies/auto-pr) ([Markdown](https://aitinkerers.org/technologies/auto-pr.md)) — 1 public demo
- [Auto Reno](https://aitinkerers.org/technologies/auto-reno) ([Markdown](https://aitinkerers.org/technologies/auto-reno.md)) — 1 public demo
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 37 public demos
- [Bun](https://aitinkerers.org/technologies/bun) ([Markdown](https://aitinkerers.org/technologies/bun.md)) — 18 public demos
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [CircleCI](https://aitinkerers.org/technologies/circleci) ([Markdown](https://aitinkerers.org/technologies/circleci.md)) — 2 public demos
- [Claude CLI](https://aitinkerers.org/technologies/claude-cli) ([Markdown](https://aitinkerers.org/technologies/claude-cli.md)) — 3 public demos