# Apache Kafka Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/apache-kafka
> Markdown URL: https://aitinkerers.org/technologies/apache-kafka.md
> Technology record last updated: 2026-02-27T08:48:08Z
> Generated: 2026-09-21T02:56:24Z

Apache Kafka is the open-source distributed event streaming platform: it handles high-throughput, fault-tolerant data feeds for real-time applications.

Kafka is your core event streaming platform, engineered for massive scale and low latency (as low as 2ms). Originally developed at LinkedIn and open-sourced in 2011, it functions as a distributed, partitioned commit log (topics) for publishing and subscribing to streams of records. The system is highly fault-tolerant and horizontally scalable, supporting clusters with thousands of brokers and processing trillions of messages daily. Key components include the Producer, Consumer, Streams, and Connect APIs, enabling everything from simple data pipelines to complex stream processing. Over 80% of Fortune 100 companies trust Kafka for mission-critical use cases (e.g., real-time analytics, event-driven architectures).

- Official technology site: https://kafka.apache.org/
- Public AI Tinkerers demos and talks: 8
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Investment Research Assistant](https://seattle.aitinkerers.org/talks/rsvp_2hF-NS5iNhE)

I have built an MVP of an AI agentic assistant along with MCP servers for real-time market data, to help equity investors research about their exiting portfolios and new stock research for US and Indian markets. I will present a working scenarios where I will fundamentally research a stock using my tool and display how this can save retail investors time and simplify their investment process.

- Event context: AI Tinkerers Seattle: January Meetup — 2026-01-31 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_2hF-NS5iNhE

### [Multi-Agent Fraud Detection: When LLMs Argue About Bitcoin Laundering](https://toronto.aitinkerers.org/talks/rsvp_l2U61QefZDs)

I built a real-time Bitcoin fraud detection system where three LLM agents debate whether a transaction is fraudulent: - Agent 1 (Prosecutor): Uses Graph RAG (Neo4j) to find suspicious network patterns and builds a case for fraud - Agent 2 (Defense): Searches for legitimate explanations and challenges the prosecutor's claims - Agent 3 (Judge): Reviews both arguments and makes the final verdict The Live Demo: 1. A suspicious transaction streams in via Kafka 2. Prosecutor Agent queries the Neo4j graph and constructs a fraud case using Gemini 3. Defense Agent counter-argues with alternative explanations 4. Judge Agent renders a verdict with confidence scoring 5. I pop the hood and show: the exact prompts, the Cypher graph queries, and the decision logic Technical Deep Dive: - How I structure multi-hop graph context for LLM reasoning - Prompt engineering to prevent agent "hallucination" on graph data - Latency battles: why I moved from Gemini Pro to Flash and added prompt caching - The surprising failure modes: when agents agree too quickly vs. when they hallucinate connections

- Event context: AI Tinkerers Toronto - January 2026 Meetup at Google! — 2026-01-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_l2U61QefZDs

### [Building an Interpretable AI Market Regime Engine](https://valencia.aitinkerers.org/talks/rsvp_ZWrBWUN_Uig)

This talk presents Zensei, an AI-powered market regime engine designed to translate complex macro and market data into structured, interpretable intelligence. Rather than predicting prices or issuing trading signals, Zensei models market risk as a hierarchy of regimes, constraints, and transitions, and uses AI to explain what changed, why it matters, and what would alter the regime next. The system combines a deterministic rules-based engine with carefully designed prompts that generate consistent, non-alarmist, human-readable explanations in real time. The demo will show how structured data, regime logic, and prompt engineering work together to produce explainable, high-signal outputs suitable for decision support.

- Event context: AI Tinkerers Valencia January Meetup — 2026-01-29 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_ZWrBWUN_Uig

### [Number Theory enpowers the World - AI, Cryptography, Otimization](https://boston.aitinkerers.org/talks/rsvp_zcUw1UfJkB0)

Title: Number Theory Empowers the World: AI, Cryptography, and Optimization Description: This talk presents how a 45-year-old mathematical discovery in number theory—specifically Egyptian fraction decomposition methods—is solving critical problems across three domains: 1. CRYPTOGRAPHY: Structural integrity verification for cryptographic keys (RSA, post-quantum, blockchain) that detects vulnerabilities traditional PKI audits miss 2. AI OPTIMIZATION: Novel approaches to transformer attention mechanisms offering 10-100× computational efficiency improvements 3. GENERAL OPTIMIZATION: New algorithmic frameworks for resource allocation, network routing, and complex scheduling problems The presentation demonstrates how fundamental mathematical research—originally focused on the unsolved Erdős-Straus Conjecture—has unexpected cross-domain applications in modern computing challenges. Drawing on 45 years of research under Carl Pomerance (Dartmouth/ University of Georgia) and Edwin Moise (Harvard/ Queens College), this talk shows how deep mathematical structures provide computational advantages that contemporary algorithms miss. Key takeaways: - How Egyptian fraction theory applies to modern computing - Practical applications in cryptographic security and government infrastructure - Potential AI efficiency breakthroughs from number-theoretic methods - Why fundamental mathematics matters for technological innovation Suitable for: AI researchers, security engineers, optimization specialists, and anyone interested in the intersection of pure mathematics and practical computation.

- Event context: AI Tinkerers Boston Meetup December 2025 — 2025-12-02 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_zcUw1UfJkB0

### [What I Learned Building a Ride Share Platform for RoboTaxis](https://amsterdam.aitinkerers.org/talks/rsvp_bcWgooXQCbE)

What happens when autonomous vehicles need to communicate with passengers, dispatchers, traffic systems, and each other in real time? Building a RoboTaxi platform taught me that traditional AI architectures crumble under the complexity of large-scale multi-agent communication. In this talk, I'll share hard-won lessons from architecting a distributed AI system where hundreds of autonomous agents coordinate thousands of rides daily. You'll discover why point-to-point agent communication creates a brittle mess, and how event-driven architecture (EDA) becomes the nervous system that keeps everything connected. Through a live demo of the RoboTaxi platform, I'll show you: - How AI agents can communicate asynchronously without tight coupling - The architecture decisions that separate toy demos from production-ready AI systems Whether you're building chatbot networks, autonomous systems, or multi-agent AI applications, this session will give you the architectural foundation to scale beyond the prototype phase. Let's take this ride together.

- Event context: AI Tinkerers Amsterdam — October Edition: Agents in production — 2025-10-10 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_bcWgooXQCbE

### [The War Room: a shared workspace for specialists to handle events](https://nyc.aitinkerers.org/talks/rsvp_nwotolIL-TQ)

The same characteristics of a "War Room" that allow military industry companies to bring all-hands-on-deck and solve critical issues can be applied to pull together multiple LLM agents to work on a shared topic. It involves realtime events, processed by specialized agents, whose output is captured in a shared workspace. This offers a system for human-in-the-loop selection of actions proposed by specialized agents that are fully aware of the context. Demonstrated in the new contextFound prototype for personal information organization.

- Event context: AI Tinkerers - New York City - December 2024 Meetup — 2024-12-12 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_nwotolIL-TQ

### [Time-Bound AI Model](https://austin.aitinkerers.org/talks/rsvp_W9daxK1z0QQ)

AGI is the focus.

- Event context: August Meetup: Community AI Demos — 2024-08-08 — Austin
- Public talk page: https://austin.aitinkerers.org/talks/rsvp_W9daxK1z0QQ

### [LLM's are more than a chatbot - nutritionGPT](https://chicago.aitinkerers.org/talks/rsvp_Zbx6QskyGK0)

Using LLM's doesn't need to stop at the interface level of your computer! These modern marvels of computer power have an insurmountable amount of applications. This this demo I will be showcasing one that I was able to extract during my weekend tinkering hours. This demo showcases multiple LLM's communicating in real-time to solve and issue of "Classifying , Identifying , Searching , and Realigning on the data gathered" all relevant to nutrition! Using this power I was able to ingest an arbitrary image or string of a meal prep event and turn it back into a usable label to remind me to eat healthy!

- Event context: Chicago AI Tinkerers 2024 Kickoff — 2024-01-23 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_Zbx6QskyGK0

## Related Technologies

- [Amazon Kinesis](https://aitinkerers.org/technologies/amazon-kinesis) ([Markdown](https://aitinkerers.org/technologies/amazon-kinesis.md)) — 5 public demos
- [Apache Flink](https://aitinkerers.org/technologies/apache-flink) ([Markdown](https://aitinkerers.org/technologies/apache-flink.md)) — 4 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Apache Storm](https://aitinkerers.org/technologies/apache-storm) ([Markdown](https://aitinkerers.org/technologies/apache-storm.md)) — 2 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Google Cloud Dataflow](https://aitinkerers.org/technologies/google-cloud-dataflow) ([Markdown](https://aitinkerers.org/technologies/google-cloud-dataflow.md)) — 2 public demos
- [Google Cloud Pub/Sub](https://aitinkerers.org/technologies/google-cloud-pub-sub) ([Markdown](https://aitinkerers.org/technologies/google-cloud-pub-sub.md)) — 2 public demos
- [RabbitMQ](https://aitinkerers.org/technologies/rabbitmq) ([Markdown](https://aitinkerers.org/technologies/rabbitmq.md)) — 6 public demos
- [Redis Streams](https://aitinkerers.org/technologies/redis-streams) ([Markdown](https://aitinkerers.org/technologies/redis-streams.md)) — 3 public demos
- [Amazon Kinesis Data Streams](https://aitinkerers.org/technologies/amazon-kinesis-data-streams) ([Markdown](https://aitinkerers.org/technologies/amazon-kinesis-data-streams.md)) — 1 public demo
- [Apache Beam](https://aitinkerers.org/technologies/apache-beam) ([Markdown](https://aitinkerers.org/technologies/apache-beam.md)) — 1 public demo
- [Apache Pulsar](https://aitinkerers.org/technologies/apache-pulsar) ([Markdown](https://aitinkerers.org/technologies/apache-pulsar.md)) — 1 public demo
- [Apache Spark Structured Streaming](https://aitinkerers.org/technologies/apache-spark-structured-streaming) ([Markdown](https://aitinkerers.org/technologies/apache-spark-structured-streaming.md)) — 1 public demo
- [AWS EventBridge](https://aitinkerers.org/technologies/aws-eventbridge) ([Markdown](https://aitinkerers.org/technologies/aws-eventbridge.md)) — 1 public demo
- [Azure Event Grid](https://aitinkerers.org/technologies/azure-event-grid) ([Markdown](https://aitinkerers.org/technologies/azure-event-grid.md)) — 1 public demo
- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos