.png&w=256&q=75)
🤝 Top Collaborators
🤓 Latest Submissions
Gemma Miner: autonomous text-to-dataset agent
What I built Gemma Miner is a command-line agent that turns a one-sentence brief "build me a dataset of every CNIL sanction since 2011 with sector, fine amount, and the GDPR articles violated" into a typed Parquet dataset with a codebook and charts, in minutes. It runs locally on Gemma 4 31B through Ollama. So your data never leaves your laptop. You can also point it at hosted Gemini Flash if you want speed. Same code, same agent. Install: uv tool install gemma-miner gemma-miner That's it. PyPI: https://pypi.org/project/gemma-miner/ — repo: https://github.com/moncifem/gemma-miner Why I built it I kept hitting the same wall. The world has a lot of text. Regulatory filings, court decisions, clinical trials, news, PDFs sitting on government websites. We have foundation models that can read all of it. What we don't have is the table you need to actually study any of it. You can't run statistics on a paragraph. RAG won't tell you whether CNIL fines have grown 5× since 2014, or whether China has overtaken the US in clinical AI trials. Those questions need a typed table, columns with real types, rows with the same shape, nulls where the source was silent. The kind of dataset every social scientist or epidemiologist has been building by hand in Excel for a hundred years That's the gap I wanted to close.
19 May 2026
SupplAIChain - The Control Tower AI Agent
SuppAIChain Control Tower is a smart Supply Chain Control Tower powered by AI agents. 📦 Context: Retail Distribution Planning Retail distribution planning involves coordinating all the processes to prepare and deliver goods from central warehouses to stores across multiple cities and countries. At each step of the process, systems collect timestamps that can be used to monitor the distribution from order creation to store delivery. 🗼What is a Control Tower? A Supply Chain Control Tower is a set of dashboards that utilises these timestamps to provide end-to-end visibility and real-time monitoring of shipments, enabling teams to detect delays, understand root causes, and take corrective action. 🤖 What do we propose? SuppAIChain replaces static dashboards with an intelligent AI agent that acts like a virtual supply chain analyst—available 24/7. Built for distribution planning operations, this agent connects to a structured shipment database that tracks delivery steps from a warehouse to stores. Users can ask operational questions through chat, email, or voice, and get instant insights. The SuppAIChain has also a Code agent capable of creating code for visualisations on the fly. 🚀 Core Features SuppAIChain supports: Natural language chat interface (web-based) Email input and automated reply (via n8n workflows) Voice-to-query feature using speech recognition (text-to-speech) Structured reasoning with multi-step delay tracing using Smolagents. Adaptation to any type of database structure with an on-boarding feature helping users write system prompts describing the schema of their database to the agent. 🎯 Value Proposition The product enables business users to monitor performance without needing dashboards or SQL knowledge. It's scalable for enterprises handling high volumes of shipments and aims to modernize how teams interact with operational data faster.
8 Jul 2025
