Sphinx – the Jupyter-native AI copilot for data scientists
Hey HN community! Over the past year, AI copilots like Cursor and Windsurf have fueled a dramatic shift in software engineering workflows. And yet, many technical users in adjacent fields like data science and analytics have been unable to reap the rewards of this revolution. It turns out that the existing tools are a poor match for analytical workloads. Beyond that Cursor and similar tools have very poor support for Jupyter notebooks, data science is a fundamentally different discipline from software engineering and we believe it requires a correspondingly different tool. We're excited to…
Sphinx – the Jupyter-native AI copilot for data scientists launched on September 9, 2025 with 6 votes, #3,421 of 8,160 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 1 year on.
What it does
Sphinx is a reliability system designed for organizations that depend on accurate, trustworthy data. It ensures that definitions stay consistent across systems, reducing manual fixes and eliminating guesswork.
S p h i n x m a k e s y o u r d a t a a n d A I r e l i a b l e . Sphinx AI continuously governs and corrects your data and AI outputs. It learns how your business defines, measures, and uses data, and makes sure every AI output is accurate. Sphinx AI continuously governs and corrects your data and AI outputs. It learns how your business defines, measures, and uses data, and makes sure every AI output is accurate. Your business logic, metric definitions, and institutional knowledge are automatically captured and continuously maintained as a single, living source of truth. Your business logic, metric definitions, and institutional knowledge are automatically captured and continuously…from sphinx.ai
In the maker’s words, at launch
Hey HN community! Over the past year, AI copilots like Cursor and Windsurf have fueled a dramatic shift in software engineering workflows. And yet, many technical users in adjacent fields like data science and analytics have been unable to reap the rewards of this revolution. It turns out that the existing tools are…
Does a similar job
all alternatives →
Adding Mistral Codestral and GPT-4o to Jupyter Notebooks2024 · github.com · ▲269Hey HN! We’ve forked Jupyter Lab and added AI code generation features that feel native and have all the context about your notebook. You can see a demo video (2 min) here: https://www.tella.tv/video/clxt7ei4v00rr09i5gt1laop6/view Try a hosted version here: https://pretzelai.app Jupyter is by far the most used Data Science tool. Despite its popularity, it still lacks good code-generation extensions. The flagship AI extension jupyter-ai lags far behind in features and UX compared to modern AI code generation and understanding tools (like…
Einblick Prompt AI for JupyterLab2023 · ▲81A generative AI pair programmer optimized for data science
ViberiaMay 2026 · getviberia.com · ▲146Hey HN, This is my take on the agent harness. Everything on an isometric map. Agents are grouped into "buildings" that run in a sequence or a loop; e.g., the CodeForge has an agent that writes a PRD, another one that implements, and a third that reviews. Everything is customizable, you build your own buildings/teams however you want. It's a Tauri app, really light (about 8x less energy than the closest competitor I benchmarked, so it actually runs from a coffee shop on battery). It's macOS only for now, but ping me if you are willing to test the Windows or Linux version. I've been…
Microsoft Dragon Copilot2025 · microsoft.com · ▲140The industry’s first AI assistant for clinical workflow
- UGUnionX – GPT4-powered Copilot for Work with Jupyter-style notebooks2023 · unionx.io · ▲50
Hey HN community! We're excited to introduce UnionX, an AI Copilot for Work designed to revolutionize the way you perform research, write long documents, and extract insights. Our platform is perfect for PMs, students, lawyers, finance professionals, and more. UnionX is built on cutting-edge technology, leveraging OpenAI's GPT4 model and Jupyter notebook-style workflows to create a seamless, AI-powered experience. Our block-based editor allows you to easily upload documents, analyze them, and generate new insights or docs with the help of AI. If you don't have ideas about what to do with…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 22d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, September 2025
the whole month →
The site hit #1 on HN about a year ago. Got enough traffic that I turned it into a proper API. What's there: - REST API — 35k products, manually filterable by category, free key, 60 req/min - CLI — npx anycrap random -c food - faker.js plugin — bundled, no API call, works offline - HuggingFace dataset — full 35k rows for ML/training https://anycrap.shop/developers
AI · 2025 · anycrap.shop
I made a built-from scratch Wayland Compositor to display any GUI app* in the terminal! I think there is a lot of unexplored potential in custom Wayland compositors, a lot of really cool things you can embed existing applications into! So, I started with embedding apps into the terminal because that is the easiest input/output (output is just utf-8 and I use the great `chafa` library for that, and I just read from stdin for the input). If you have any other ideas for cool Wayland compositors, let me know. I purposedly wrote 80% the app in Typescript to appeal to the most developers and…
Dev tools · 2025 · github.com
- IR
Years ago I stumbled across a basic version of this concept and it stuck with me. I knew if I was ever going to take on such a project, it would need to be flawless, but without coding experience it was just another idea that would never happen. By the end of 2024, as AI coding tools exploded everywhere, I finally had a way to make it real. I started from zero knowledge and spent months collaborating with AI agents as a learning experience. Every pixel and every function went through me. The AI translated what I asked for into code, but every decision was human. I didn't use existing OS…
AI · 2025 · mitchivin.com
