# Groq Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/groq
> Markdown URL: https://aitinkerers.org/technologies/groq.md
> Technology record last updated: 2026-09-18T15:13:59Z
> Generated: 2026-09-20T18:42:00Z

Groq delivers ultra-fast AI inference using its custom-built Language Processing Unit (LPU) to accelerate Large Language Models (LLMs) at scale.

Groq specializes in high-speed AI inference, leveraging its proprietary Language Processing Unit (LPU) Inference Engine: a chip specifically architected for generative AI and LLMs. The LPU's unique dataflow architecture bypasses the memory and compute bottlenecks of traditional GPUs, delivering consistent, ultra-low-latency performance and superior energy efficiency. This technology, accessible via the GroqCloud platform or on-premise GroqRack clusters, enables real-time application deployment for demanding enterprise customers. Founded in 2016 by former Google engineers (including a lead designer of the TPU), Groq is setting the new standard for real-time AI compute.

- Official technology site: https://groq.com
- Public AI Tinkerers demos and talks: 23
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Video killed the radio star - giving uses the choice of audio, video or text chat](https://portland.aitinkerers.org/talks/rsvp_Q6eRu-RS-Y0)

I will be demoing and discussing Mebot AI's product for creating digital twins, which lets users make a 2-minute video that can clone their voice and video for photorealistic real-time interaction. It takes about 15 minutes for the AI audio interviews, and that is then turned into your personality and style. Your twin can join via audio or video meetings on Zoom, Teams, Google Meet, Slack, and many others.

- Event context: AI Tinkerers Portland: Building Voice Agents & Conversational AI Stacks — 2026-03-06 — Portland
- Public talk page: https://portland.aitinkerers.org/talks/rsvp_Q6eRu-RS-Y0

### [Engineering a Consistent Image Gen Pipeline for Augmentative and Alternative Communication](https://valencia.aitinkerers.org/talks/rsvp_Y29X1ZoMALk)

I’ll demo how I built an AI-powered pictogram workflow that combines three components: 1. An offline prompt-to-image matching architecture that maps user intent to the most relevant pictograms (generated or existing), including how I represent prompts, store image/text embeddings locally, and select candidates with lightweight retrieval—so the experience stays fast and consistent. 2. Pictogram generation using an image generation model (prompt → pictogram), including the constraints and post-processing steps I use to maintain a consistent pictogram style and usable output format. 3. A lightweight “AI builder” workflow that assembles pictograms into simple compositions, focusing on the interaction model and the data structures that make the builder feel like a practical tool rather than a one-off generator. The demo will walk through each workflow step-by-step, paired with technical implementation notes and lessons learned around consistency, latency, and reliability.

- Event context: AI Tinkerers Valencia January Meetup — 2026-01-29 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_Y29X1ZoMALk

### [Neural Probing LLMs for 'Immediate Inference'](https://montreal.aitinkerers.org/talks/rsvp_qy_wNEb75lc)

'Training' is an ongoing challenge but 'Inference' will be the dominant performance challenge of AI going forward, signalled by Groq acquisition by Nvidia. Autogeneration is slow and expensive, and it's now the dominant 'bottleneck'. 'Probing' or adding novel architectures onto LLMs (Heads) can accelerated inference by measuring the 'state' of an LLM side-stepping the requirement to generate tokens. I don't have a super fancy presentation or clean GitHub yet, it's just lab notes and demo. It actually works, this is serious, not just a toy.

- Event context: AI Tinkerers Montreal - January 2026 Meetup at Ateko — 2026-01-21 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_qy_wNEb75lc

### [AI quantitative analysis education coach](https://boston.aitinkerers.org/talks/rsvp_5oUCjtPtYCo)

This is for a learning coach I made at a Hackathon last month for people learning to be quantitative traders

- Event context: AI Tinkerers Boston Meetup November 2025 — 2025-11-17 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_5oUCjtPtYCo

### [Making Therapy Open Source](https://berlin.aitinkerers.org/talks/rsvp_wGZLsOItEMU)

A live demo of a LiveKit based therapy voice agent that learns from your interactions. It pushes you when you're being toxic and is understanding of the struggles in your life. Fully self-hostable therapist/life-coach with all the privacy you'd want.

- Event context: AI Tinkerers Berlin Meetup - November 12th, 2025 — 2025-11-12 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_wGZLsOItEMU

### [Life bricks: A chronicle of building an app with AI.](https://st-louis.aitinkerers.org/talks/rsvp_jiqI16zFGfE)

My experience with vibe coding, code walk through the demo, prompts used for retrieving llm analysis.

- Event context: AI Tinkerers - St. Louis October Meetup — 2025-10-22 — St. Louis
- Public talk page: https://st-louis.aitinkerers.org/talks/rsvp_jiqI16zFGfE

### [AutoGrading Student Answers using](https://dubai.aitinkerers.org/talks/rsvp_nZAAyR1_6s0)

I implemented a full scale autograding solution for written and spoken answers for 1million userbasr 25k concurrent users. We used whisper and llama. On different providers to meet the scale.

- Event context: AI Tinkerers Dubai Meetup — August 2025 Demo Day — 2025-08-23 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_nZAAyR1_6s0

### [Getting models to speak what you want](https://riyadh.aitinkerers.org/talks/rsvp_xk5IVKpOJRo)

This demo covers the difference between using a plain generic LLM, and then making it "speak" the way you want through approaches like RAG architecture and fine-tuning.

- Event context: AI Tinkerers – Riyadh Inaugural Demo Meetup · August 19th, 2025 — 2025-08-19 — Riyadh
- Public talk page: https://riyadh.aitinkerers.org/talks/rsvp_xk5IVKpOJRo

### [AutoCoder](https://singapore.aitinkerers.org/talks/rsvp_6YvZMf5gv50)

A really, really fast pair programmer(similar to Claude Code)(but using groq/cerebras) under the hood

- Event context: AIT Singapore: scalable agentic workflows - 12th August 2025 — 2025-08-12 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_6YvZMf5gv50

### [Anywhere MCP Mobile App](https://orange-county.aitinkerers.org/talks/rsvp_k3LbAklRqlY)

A comprehensive Model Context Protocol (MCP) platform that enables seamless AI tool integration across multiple devices. Anywhere MCP provides both real-time voice interactions through WebRTC streaming and REST API endpoints, allowing developers to connect AI agents with external tools and services anywhere - from web browsers to mobile apps to command-line interfaces. The roadmap for the platform will implement advanced agentic workflows including recursive planning, intelligent tool selection, and self-correction mechanisms, allowing AI agents to autonomously compose complex multi-step operations using external services like databases, APIs, file systems, and cloud resources. Code Examples: Real-time Tool Discovery & Validation ``` @log_mcp_operation("MCP tool registration") async def register_tools(self, session_id: str, tools: List[MCPTool]) -> RegistrationResult: # Dynamic schema validation with concurrent processing validation_service = get_validation_service() for tool in tools: validation_result = await validation_service.validate_tool(tool) if not validation_result.valid: # Self-healing: attempt parameter correction corrected_tool = await self._auto_correct_tool_parameters(tool) ``` Concurrent Session Management Architecture ``` class MCPSessionService: def __init__(self): self.max_tools_per_session = 50 self.session_tool_ttl = 24 * 60 * 60 # 24 hours @retry_on_redis_error(max_retries=3) async def execute_tool(self, tool_name: str, parameters: Dict[str, Any], session_id: str): # Handles 1000+ concurrent sessions with sub-200ms latency ``` Cross-Platform State Synchronization ``` // Vue.js composable maintaining real-time state across modalities export const useMCPSession = () => { const sessionTools = ref>(new Map()) const serverStatus = ref>(new Map()) // Real-time synchronization between WebSocket, REST, and mobile const syncToolState = async (sessionId: string) => { const response = await mcpApi.getSessionTools(sessionId) sessionTools.value.set(sessionId, response.tools) } ```

- Event context: AI Tinkerers - Orange County Meetup- Thursday July 31st 2025 — 2025-08-01 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_k3LbAklRqlY

### [How we built one of the most accurate computer use agent, and how we are scaling it](https://singapore.aitinkerers.org/talks/rsvp_vW5udx_0XgA)

We would be presenting Iris, which is a computer use agent, with capabilities for reading files, connecting to mcp servers and others. It can browse computer like a normal user, read files etc...

- 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_vW5udx_0XgA

### [Claudio AI Musician](https://milan.aitinkerers.org/talks/rsvp_lxUiuQMNPYs)

A short demonstration of AI Agents for music production, the agents collaborate with the user to control a FM Synthesiser and jam together to create a dataset that will be used to train a more personalised AI tailored to the users musical tastes and needs.

- Event context: AI Tinkerers Milan - June 10, 2025 - Community Demos & Networking — 2025-06-10 — Milan
- Public talk page: https://milan.aitinkerers.org/talks/rsvp_lxUiuQMNPYs

### [Voice AI, Duolingo that works](https://waterloo.aitinkerers.org/talks/rsvp_VjQQY_9bWnY)

I will be presenting my NextJS Hackathon Project Building a learning tool to communicate with AI in a language the user is learning

- Event context: AI Tinkerers - Waterloo April Meetup — 2025-04-21 — Waterloo
- Public talk page: https://waterloo.aitinkerers.org/talks/rsvp_VjQQY_9bWnY

### [Your technical interviews sucks, so let's fix it.](https://medellin.aitinkerers.org/talks/rsvp_SBkLNboksM0)

This project is built to provide real-time voice interactions using the Realtime API and Chainlit. Melissa acts as an agent that calls various tools to handle user requests and performance as a technical interviewer to interact with.

- Event context: AI Tinkerers Medellín #11 - Science Fair - Agentes en acción — 2025-04-01 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_SBkLNboksM0

### [Groq multi-modal agentic demo](https://dublin.aitinkerers.org/talks/rsvp_yGG1-3QKhbo)

Showcasing real-time multimodal and agentic open source demos powered by Groq as well as a quick dive into the code base behind them

- Event context: AI Tinkerers Dublin (March) — 2025-03-26 — Dublin
- Public talk page: https://dublin.aitinkerers.org/talks/rsvp_yGG1-3QKhbo

### [Introduction Groq - world's fastest AI inference](https://singapore.aitinkerers.org/talks/rsvp_o2UoRjDZ0W8)

Groq builds fast AI inference technology. Groq® LPU™ AI inference technology is a hardware and software platform that delivers exceptional AI compute speed, quality, and energy efficiency. Groq, headquartered in Silicon Valley, provides cloud access to popular models, via the GroqCloud, and on-prem solutions at scale for AI applications. The LPU and related systems are designed and manufactured in North America.

- Event context: AI Tinkerers Singapore: 5th Meetup - February 21st, 2025 — 2025-02-21 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_o2UoRjDZ0W8

### [Doomscroll Detector](https://nyc.aitinkerers.org/talks/rsvp_3psMs9q4VbQ)

Catches you in the act of doomscrolling. When it does, summarizes all the things you glossed over into a series of discussion points for you to actually spend time to think about.

- Event context: AI Tinkerers - New York City - November 2024 Meetup | Win Meta Ray-Bans — 2024-11-12 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_3psMs9q4VbQ

### [podscript - CLI tool to generate podcast transcripts using language and speech-to-text models](https://bengaluru.aitinkerers.org/talks/rsvp_qNRKpmz9GJM)

podscript is a tool to generate transcripts for podcasts (and other similar audio files), using LLMs and other Speech-to-Text (STT) APIs. Currently, ChatGPT, Anthropic, Deepgram and Groq are supported.

- Event context: AI Tinkerers Bangalore - October - RSVP REQUIRED — 2024-10-17 — Bengaluru
- Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_qNRKpmz9GJM

### [AI-Driven Triage Automation: Voice-to-Text with Groq for Emergency Care](https://dubai.aitinkerers.org/talks/rsvp_RQGteQRFzsM)

This session will dive into how Groq's AI models can be applied to automate triage documentation in emergency care. Using a real-world implementation, we’ll demonstrate how paramedic or doctor statements can be transcribed using the Whisper-large-v3 model, and automatically converted into structured JSON data for patient records. The code leverages Groq’s transcription capabilities and LLaMA3-70B for generating structured data that populates triage forms, saving critical time in emergencies. The presentation includes a detailed walkthrough of the code, covering everything from uploading the audio file to generating the structured output, along with a live demo.

- Event context: AI Tinkerers - Dubai Inaugural Meetup (September) — 2024-09-07 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_RQGteQRFzsM

### [Groq LPU™ AI Inference Technology](https://seattle.aitinkerers.org/talks/rsvp_1ex4w1Ki5Z4)

MAIN STAGE: Groq is presenting some cool demos of AI applications and use cases running on the Groq LPU™ AI Inference Technology, complete with their GitHub repos.

- Event context: AI Tinkerers Summer Social - August 2024 — 2024-08-16 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_1ex4w1Ki5Z4

### [Autocomplete.sh - LLM Powered Bash Completion](https://boston.aitinkerers.org/talks/rsvp_iuakg6mCh4s)

This is open source software that connects language models directly into the terminal in order to perform a smart 'autocomplete' for us in the command line. I just released v0.3 which supports most language models: Ollama, Groq, Anthropic, OpenAI Just open the command line and write a sentence, describing the task and hit and you'll see 2-5 suggestions almost immediately pop onto your screen. This is MUCH FASTER and more customized than googling or copy and pasting from ChatGPT.

- Event context: July 2024 Meetup at C10 Labs — 2024-07-22 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_iuakg6mCh4s

### [Bubble Up](https://denver-boulder.aitinkerers.org/talks/rsvp_01wknOngNWM)

Demo from our Meta/Llama3 hackathon project

- Event context: AI Tinkerers Denver - June Meetup — 2024-06-11 — Denver
- Public talk page: https://denver-boulder.aitinkerers.org/talks/rsvp_01wknOngNWM

### [Multimodal Groq Demo](https://denver-boulder.aitinkerers.org/talks/rsvp_TiwUC6zS46U)

Groq is the leading low-latency AI inference provider, and we've been cooking up some magic! Demo gods permitting, we'd love to show a sneak peek of some voice and multimodal models we have running on our hardware.

- Event context: AI Tinkerers Denver - June Meetup — 2024-06-11 — Denver
- Public talk page: https://denver-boulder.aitinkerers.org/talks/rsvp_TiwUC6zS46U

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Deepgram](https://aitinkerers.org/technologies/deepgram) ([Markdown](https://aitinkerers.org/technologies/deepgram.md)) — 11 public demos
- [ElevenLabs](https://aitinkerers.org/technologies/elevenlabs) ([Markdown](https://aitinkerers.org/technologies/elevenlabs.md)) — 42 public demos
- [Llama 3 70B](https://aitinkerers.org/technologies/llama-3-70b) ([Markdown](https://aitinkerers.org/technologies/llama-3-70b.md)) — 3 public demos
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [Streamlit](https://aitinkerers.org/technologies/streamlit) ([Markdown](https://aitinkerers.org/technologies/streamlit.md)) — 89 public demos
- [AI](https://aitinkerers.org/technologies/ai) ([Markdown](https://aitinkerers.org/technologies/ai.md)) — 55 public demos
- [AI inference](https://aitinkerers.org/technologies/ai-inference) ([Markdown](https://aitinkerers.org/technologies/ai-inference.md)) — 1 public demo
- [Amazon Bedrock](https://aitinkerers.org/technologies/amazon-bedrock) ([Markdown](https://aitinkerers.org/technologies/amazon-bedrock.md)) — 20 public demos
- [Anthropic](https://aitinkerers.org/technologies/anthropic) ([Markdown](https://aitinkerers.org/technologies/anthropic.md)) — 36 public demos
- [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos
- [Bhumi](https://aitinkerers.org/technologies/bhumi) ([Markdown](https://aitinkerers.org/technologies/bhumi.md)) — 1 public demo
- [Cerebras](https://aitinkerers.org/technologies/cerebras) ([Markdown](https://aitinkerers.org/technologies/cerebras.md)) — 3 public demos
- [Chainlit](https://aitinkerers.org/technologies/chainlit) ([Markdown](https://aitinkerers.org/technologies/chainlit.md)) — 3 public demos
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [Convex](https://aitinkerers.org/technologies/convex) ([Markdown](https://aitinkerers.org/technologies/convex.md)) — 5 public demos