Pantheon-CLI – Open-Source Python Claude Code and Smart Notebook
Hi, We’ve built Pantheon-CLI, an fully open-source project that aims to be the “Python Claude Code + Notebook” — but designed for data analysis instead of just coding. Unlike most AI coding assistants, Pantheon-CLI runs entirely on your machine (or server). No data upload required. It blends natural language and code in a single workflow, keeping variables in memory and letting you switch seamlessly between typing code and asking in plain English. What it does: 1. Chat with your data: Directly process CSV, Excel, AnnData, Pickle, Torch tensors, or any format supported by…
What it does
In the maker’s words, at launch
Hi, We’ve built Pantheon-CLI, an fully open-source project that aims to be the “Python Claude Code + Notebook” — but designed for data analysis instead of just coding. Unlike most AI coding assistants, Pantheon-CLI runs entirely on your machine (or server). No data upload required. It blends natural language and code in a single workflow, keeping variables in memory and letting you switch seamlessly between typing code and asking in plain English. What it does: 1. Chat with your data: Directly process CSV, Excel, AnnData, Pickle, Torch tensors, or any format supported by Python/R/Julia. 2. Mixed programming: Variables persist across natural language and code; the CLI auto-generates and runs code for you. 3. MCP-like agent integration: Read/create files, run commands, fetch web pages, generate/revise code. 4. Human-like learning: Feed it a PDF paper or tutorial—Pantheon-CLI reads it, plans steps, and replicates methods before analysis. 5. Task planning: Builds scientific agents by learning from papers/tutorials (not just fixed, human-predefined steps). 6. Multi-model support: Works with OpenAI, Anthropic, Gemini, DeepSeek, Qwen, etc. + offline local LLMs (ollama, deepseek, gpt-oss). 7. Multi-RAG support: Pre-learns from docs/web into a local “brain” for more credible outputs without massive token costs. 8. Built-in biology toolsets: For omics analysis (alignment, annotation, differential expression, full paper reproduction). 9. Notebook mode: Brings the same agentic workflow into Jupyter—automatically runs and revises code, operates on files, and learns from tutorials/papers. Pantheon-CLI is our attempt to push beyond “AI writes code for you.” Instead, it’s an agentic operating system for data analysis, spanning both terminal and notebook. Repo: https://github.com/aristoteleo/pantheon-cli Tutorial: https://pantheonos.stanford.edu/cli/docs/intro/getting-start... Home page: https://pantheonos.stanford.edu/ Would love to hear feedback from the HN community—what use cases would you try this for, and what features would make it more useful to you?
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca