🚀 Cut Latency, Ditch the Cloud: Our Hottest AI Tinkerers Demos - July 28 [AI Tinkerers - Post-Training] .

🚀 Cut Latency, Ditch the Cloud: Our Hottest AI Tinkerers Demos - July 28

Joe Heitzeberg
Joe Heitzeberg — AI Tinkerers - Post-Training
July 28, 2025

AI Tinkerers

🚀 Cut Latency, Ditch the Cloud: Our Hottest AI Tinkerers Demos - July 28

Issue #1 · Week of July 28

Recent live demos from London, DC and Tiruchirappalli: a monetized Remote MCP on Cloudflare Workers + Supabase + Stripe; Aura, a local Qwen2-VL + Mistral 7B gaming companion with sub-3s responses; and Survaize, vision/OCR -> JSON -> ODK. All ran live with repos; these are the demos we’re still thinking about.

Top 5 Picks (July 28)
1 TOP PICK

Sourcebot: Agentic Codebase Understanding

Profile photo

Brendan K.

Co-Founder at Sourcebot

Brendan Kellam from Sourcebot demo’d Sourcebot, a self-hosted tool to help you understand your codebase. Sourcebot provides flagship reasoning models the ability to search and navigate your codebase, allowing them to answer complex natural language questions. It summarizes these findings in a modern web UI that includes inline citations, allowing the answers to be grounded in navigable references into your codebase.
2 RUNNER UP

Helpful Computer

Profile photo

Ron Lancaster

CTO at Internet Testing Systems (ITS)

Helpful Computer was a demo that showed off an interactive voice agent interacting with Excalidraw and Lexical, all built via Tauri. Ron, a seasoned tech leader from ITS, presented it and demonstrated how a voice interface could effectively collaborate with creative tools. People loved its practicality and clear demonstration of agent use, hinting at business potential in streamlining creative collaboration and everyday communication for both startups and larger organizations.
PROJECT LINKS
github.com Video
3 COMMUNITY FAVORITE

Voice Trivia Bot

Profile photo

William Horton

Staff Software Engineer, AI/ML at Maven Clinic

William showcased the Voice Trivia Bot demo, an app that read quiz bowl questions aloud from PDFs and let users buzz in with audio answers that were graded against the official responses. William, a staff engineer with a solid background in AI and healthcare at Maven Clinic, built the app using OpenAI APIs and Cursor with LLM coding assistants. People loved how it combined multimodal interactions with a playful twist, hinting at practical applications in interactive testing and self-paced learning.
PROJECT LINKS
@hortonhearsafoo
4 STANDOUT

HackerNews.coffee: transparent fast personalization

Profile photo

Aleksi Tukiainen

Co-Founder and CEO at Arctal

Aleksi Tukiainen and Leo Browning from ClimateAligned presented HackerNews.coffee, a lean AI recommendation system that transparently personalized content by bootstrapping minimal user data. The demo showcased a practical tradeoff between fast and smart LLMs while keeping recommendations editable for users. It was a neat example of how you can ship a working system rapidly without sacrificing user control (people loved it). This practical approach offers valuable insights for builders facing similar personalization challenges.
PROJECT LINKS
hackernews.coffee
5 NOTABLE

Living Systems: AI Plant Automation

Profile photo

Aditya Prabhu

AI Engineer at Ryan Companies Inc

Aditya Prabhu presented his project, Living Systems, which built a smart plant automation system using LLMs and MQTT. The demo showcased a practical solution that controlled pumps, lights, and water levels through a React and Python interface. Drawing from his hands-on engineering background, Aditya impressed many with his down-to-earth approach. People loved how it tackled real indoor farming challenges, showing clear potential for a product that makes everyday grow shelves smarter and more connected.

More Great Builds
Quick hits from the community — demos worth bookmarking:
It was a fast-paced demo showing how to build a monetized remote MCP server in a weekend using Cloudflare Workers, Supabase, and Stripe, with Dialer handling outbound calls. Josh Warwick, Ark’s CTO, shared practical notes on a frictionless OAuth flow and tying auth to real backends. Audience feedback was strong about the hands-on value. The talk stood out by showing MCP as a deployable, revenue-ready app and gave concrete patterns for shipping AI-native connectors quickly.
Loading tech tags...
Jacques Joubert, a software engineer at Kigo, demoed his Rust GOAP library, showing how to compose plans from state to action for AI agents across domains. He walked through examples and noted how GOAP could slot into hybrid workflows with LLMs and MCP-style servers. The Rust implementation emphasized performance and clear, testable action schemas. Survey feedback hinted at its approachable, interpretable approach. This was a building block for game AI and automation, with potential for modular agent systems in products.
Loading tech tags...
Profile photo
Brian C JordanAI Tinkerers - DC Metro • Jul 10
Aura delivered a cool real-time solution that captured gameplay, recognized screen actions, and provided voice commentary using computer vision, speech recognition, and voice synthesis. Brian—a product manager who loves learning by doing—showcased how open-source tools could run efficiently on consumer-grade hardware. People loved its practical take on multimodal AI integration, and it offered developers a clear blueprint for building interactive, self-hosted gaming experiences that could adapt to a wide range of applications.
Loading tech tags...
Ecocraft Designer demonstrated how AI could streamline NBC-compliant 2D-to-3D floor plan creation. Joseva A, a rising talent from Green Build AI and a civil engineering student, used generative models and AI prompt enhancements to simplify sustainable design. Attendees appreciated the clear technical insights and practical demo that tackled eco-friendly building guidelines. This project showed strong business potential for regulatory automation while offering valuable inspiration for builders interested in sustainable construction.
Loading tech tags...
Craig demonstrated Vibe Coding with Bolt by showing how he quickly turned ideas into visual prototypes that spurred effective customer conversations. His proven experience in data center solutions and project management lent real-world credibility to the demo. People loved seeing how simply a rough code prototype could clarify system designs. This practical approach is a solid reminder for builders that rapid visual communication can bridge the gap between ideation and full development, helping quickly align teams and stakeholders.
Loading tech tags...
Josh Handley showcased Survaize, a demo that used vision models to read survey forms and automatically generate mobile data collection apps. The demo extracted questions and responses from PDFs into a structured JSON format with LLM-based validation. People loved how it tackled tedious manual data entry, and it's a practical example for developers. Josh's solid background as a full-stack engineer shone through, and the project holds promising potential for streamlining survey processes in real-world applications.
Loading tech tags...

🎬 Latest Content

How to Ship Complex Features 10x Faster with AI Agents | Dex Horthy (HumanLayer)

One-Shot • Mar 04
Dex Horthy (HumanLayer) breaks down the “12 Factor Agents” approach to shipping multi-step agentic workflows faster: structured outputs, ...
Watch Now →

How to Run Open-Source LLMs Locally on a Mac with MLX-LM

Deep Dive Series • Jun 12
Run open-source LLMs locally on Apple Silicon with Apple’s MLX-LM: `pip install mlx-lm`, then `load()` a Hugging Face model and call `gen...
Read More →

💼 Top Job Matches
Matched based on your meetup activity and profile
Paxos Health • New York & Toronto • $110k - $175k (varies w/ location/level); generous equity
Stanford-founded Seed-stage healthcare AI startup with >$5M in VC funding and AI agents deployed in production with cu...
Apply Now →
Dex • London (5 days on-site) • £250,000
Frontier AI engineering role building the AI tooling layer for complex financial modelling.
Apply Now →
Jakib AI • Columbus, OH
Jakib is a profitable, growing applied AI firm embedded with operator-led companies in logistics, manufacturing, and c...
Apply Now →

Ready for more?

Check out other posts from this blog.

View all posts