Groq

Groq, Inc. is a company specializing in artificial intelligence (AI) hardware and software solutions. Founded in 2016 by ex-Google engineers, Groq focuses on delivering AI acceleration technologies to power next-generation applications across industries. With its deterministic approach to computation, Groq redefines performance and efficiency in AI inference tasks, providing scalable and developer-friendly solutions.

Headquartered in Mountain View, California, Groq operates globally, with additional offices in Canada, Europe, and other parts of the United States. Their solutions are tailored to meet the demands of enterprises seeking high-speed AI capabilities with a focus on reliability and cost efficiency.

General Information

Attribute	Details
Author	Jonathan Ross, CEO and Founder of Groq
Company	Groq
Founded	2016
Documentation	Groq Libraries
Github repository	https://github.com/groq
Discord	https://discord.com/invite/groq
technology Type	AI Accelerator Hardware and Software Solutions

Products and Services:

Language Processing Unit (LPU): Groq's LPU is architected from the ground up with a software-first design to meet the unique characteristics and needs of AI. It offers a deterministic execution model, eliminating traditional hardware bottlenecks and providing seamless scalability.
GroqCloud: A developer-centric platform that provides API access to Groq’s high-performance AI models. GroqCloud supports a range of applications, from vision and language processing to real-time inference tasks, delivering low-cost and high-quality results.
AI Models and API Access: Groq offers a range of AI models accessible via APIs, including vision models like Llama 3.2 11B Vision 8k and Llama 3.2 90B Vision 8k. These models are designed to provide high-quality, real-time inference for various applications.

How to Start Building with Groq

To begin leveraging Groq’s high-performance AI solutions, start by exploring their development environment. Developers can tap into GroqCloud for seamless API access to pre-trained models or optimize their own AI workloads using Groq's Language Processing Unit (LPU).

Visit Groq's GitHub repository to download SDKs, tools, and libraries required for your development.

Start building with Groq 👉 https://console.groq.com/login

Web Retrieval Agent: Answers With Proof

Web Retrieval Agent is an AI agent that takes a plain-English question, searches the live web, reads the actual pages and returns only the specific information the user asked for, together with the exact quote that proves it. Most AI search tools write a fluent answer and ask you to trust it. This agent treats the language model as untrusted. It plans targeted search queries, uses Tavily to search and extract full page text, and asks the LLM (gpt-oss-120b on Groq) for a structured answer with verbatim evidence quotes. The server then checks every quote against the real page text and drops any that do not appear. If the answer contains a figure that the quotes do not support, confidence is lowered and the user is warned. If the sources do not contain the answer, the agent says so instead of guessing, and it can retry once with refined queries focused on a likely site. The interface streams the agent's activity live (planning, searching, reading, verifying), then shows the answer, a confidence meter, the proof quotes with source links and every source checked. It is built with Next.js and TypeScript and deployed on Vercel. The LLM client works with any OpenAI-compatible endpoint, so the model can be swapped for an open model served on AMD GPUs.

SCORPGUARD: The AI Agent Runtime Guardian

86% of enterprise AI agents fail in production. Not because of bad models, but because of broken runtime infrastructure. Container restarts erase agent memory, hallucinated data silently corrupts workflows, and runaway token costs breach budgets. SCORPGUARD is the Agent Runtime Guardian that solves this "last mile" problem. It acts as an intelligent middleware layer that wraps around any AI agent, ensuring safe, cost-effective, and reliable execution. Key Features: - Event-Sourced State Persistence: Uses PostgreSQL to checkpoint agent state, ensuring memory survives container restarts. - Dual-Layer Anomaly Detection: Layer 1 (Rule-Based) catches fatal crashes and loops in under 10ms. Layer 2 (Semantic AI) uses LLM inference to catch logical hallucinations and silent errors. - Auto-Rollback Engine: Instantly rewinds agent state to the last safe checkpoint upon detecting an anomaly, preventing cascading failures. - Real-Time Cost Monitor: Tracks token usage and USD cost per agent action. Built for the AMD Developer Hackathon ACT III, SCORPGUARD is architected to run on AMD Instinct MI300X using ROCm and vLLM (Qwen2.5). For high availability and demonstration, we implemented a robust fallback using Groq's API for ultra-fast LLM inference. The backend is powered by FastAPI, Celery, and Redis, with a real-time dark-theme command center for monitoring.

Wasel

Sellers in Tunisia take orders in chat and are paid in cash on delivery. A refused parcel is a wasted courier trip. Customers write in Darija (Arabic script or Arabizi), French or a mix, and give addresses like "near the mosque". Wasel reads the conversation, extracts the order and scores the refusal risk from 0 to 100, with reasons quoted from the customer's own words. It drafts the one question that would lower the risk: confirm, complete the address, or pay first. When the customer answers, the order is rescored and the page shows which reasons changed. Order #2601 goes from High 87 to Low 16 once a full address arrives. A person approves what is sent. The language model never picks a number. It fills a 12-field schema, code checks every quote against the original text, and an XGBoost model plus the rules in config/scoring.yaml compute the score. Drafts come from approved templates; any model rewrite must pass a prefilter, a classifier and a judge. Injected text in a message is flagged. Business value: in a simulation on 2,001 held-out orders, confirmation and prepayment questions cut refusals from 30.0 % to 23.6 %, worth 464 TND per 1,000 orders (labels simulated, assumptions shown in the app). Tested on every change: 279 extraction cases, 165 outbound drafts, 32 injection attempts and 737 tests that run without keys. AMD: the model call goes through a configurable route: AMD Token Factory (Gemma-4-31B-IT) first, hosted Groq (gpt-oss-120b) as a fast backup, then rules. On 40 extraction cases, Token Factory recognised 92.5 % of orders against 87.5 % for Groq (one run, synthetic data). It takes 7 to 13 s per call, so the route allows 16 s before falling back. We make no claim about the GPU. The demo uses synthetic data. Open source under the MIT licence.

Factory Agent: AI Quality & Maintenance Assistant

Factory Agent is an end-to-end AI quality inspection and industrial maintenance assistant designed for modern manufacturing environments. It addresses costly equipment downtime and the safety risks of unverified AI recommendations through multimodal defect detection, retrieval-augmented generation (RAG), evidence-grounded diagnosis, and human-in-the-loop governance. The system accepts machine-part photographs, sensor telemetry reports in CSV, JSON, or TXT formats, and technical inspection documents in TXT or PDF formats, including OCR-based text extraction. For visual inspection, Factory Agent combines an advisory local CNN with AMD Token Factory vision models, including Qwen3.8-Flash-Next and Gemma-4-31B-IT. It evaluates individual model predictions rather than averaging confidence scores, flagging low-confidence results and disagreements as UNVERIFIED for expert review. Its RAG pipeline retrieves relevant maintenance procedures from technical manuals. Primary and fallback language models, MiMo-V2.6-Flash and DeepSeek-V4-Flash, generate diagnostic explanations and repair recommendations grounded in retrieved evidence. The system validates recommendations against source manual text and provides citations identifying relevant manuals and pages where available. A human-in-the-loop interface enables plant managers to review predictions, examine supporting evidence, and approve or reject proposed maintenance actions. Only approved cases proceed to Evolus automation workflows for maintenance work-order generation. Built with Next.js, React, TypeScript, FastAPI, PyTorch, and Docker, Factory Agent supports cloud integrations and an offline mock mode for demonstrations and development without API keys. By combining automation, traceable evidence, and human oversight, Factory Agent aims to make industrial AI safer, more transparent, auditable, and practical.

MRI Vision Core AMD: Evidence Review

MRI Vision Core AMD is a research and demo workflow for inspectable knee-MRI analysis. A bridged trained Attention-MIL checkpoint processes an available MRI study and produces twelve raw, uncalibrated research-model scores with provenance. Those scores are placed into a structured EvidenceBundle. The deterministic review sequence then runs Specialist, Critic, and Consensus stages. Specialist groups existing scores without changing them; Critic checks evidence structure, provenance, quality state, and other review conditions; Consensus sets the workflow status. Every case remains pending named human review, where a reviewer can approve, request more evidence, or escalate. An optional explanation layer supports AMD Token Factory, Groq, or a local deterministic provider. It receives allowlisted review evidence and returns four reviewer-facing summaries. It is advisory only: it cannot change model scores, deterministic workflow status, or human approval. The project includes a reproducible 22-study benchmark: 22 of 22 successful inference runs, 100 percent coverage, zero failures, macro ROC-AUC 0.599, macro PR-AUC 0.485, and mean latency 0.987 seconds. These are research results against competition reference labels, not clinical validation or diagnostic claims.

AnalystOS — Your AI-Powered Business Analyst

AnalystOS — From Questions to Clarity Businesses have plenty of data, but finding meaningful answers is still difficult. Dashboards show what is happening, yet understanding why often requires hours of analysis, technical expertise, and investigation across multiple data sources. AnalystOS is your AI-powered business analyst, helping turn business questions into evidence-backed insights. Ask questions in plain language, such as “Why did sales decline this month?” AnalystOS helps investigate the question, examine relevant data, explore contributing factors, and bring the findings together into an understandable outcome. More than a chatbot, AnalystOS provides a workspace for ongoing investigations. Each Analysis preserves relevant discoveries, assumptions, decisions, unresolved questions, and analytical assets, allowing users to revisit previous work and build on it through follow-up conversations. Key capabilities: • Investigate business questions beyond a single response. • Explore the factors behind sales, customer, product, and marketing trends. • Connect findings to supporting evidence, queries, and results. • Preserve analytical context across conversations. • Create reusable assets, including findings, tables, charts, and queries. • Keep people in control of conclusions and business decisions. Designed initially for commerce analytics, AnalystOS helps teams explore business performance without requiring every user to write queries or understand complex database structures. Our vision is to make business intelligence an ongoing process of asking better questions, investigating evidence, and building lasting knowledge. AnalystOS brings this process into one intelligent workspace, helping businesses spend less effort finding answers and more effort understanding what those answers mean.