[HN Gopher] Show HN: Erdos - open-source, AI data science IDE
___________________________________________________________________
Show HN: Erdos - open-source, AI data science IDE
Hey HN! We're Jorge and Will from Lotas (https://www.lotas.ai/),
and we've built Erdos, a secure AI-powered data science IDE that's
fully open source (https://www.lotas.ai/erdos). A few months ago,
we shared Rao, an AI coding assistant for RStudio
(https://news.ycombinator.com/item?id=44638510). We built Rao to
bring the Cursor-like experience to RStudio users. Now we want to
take the next step and deliver a tool for the entire data science
community that handles Python, R, SQL, and Julia workflows. Erdos
is a fork of VS Code designed for data science. It includes: - An
AI that can search, read, and write across all file types for
Python, R, SQL, and Julia. Also, for Jupyter notebooks, we've
optimized a jupytext system to allow the AI to make faster edits.
- Built-in Python, R, and Julia consoles accessible to both the
user and AI - Plot pane that tracks and organizes plots by file
and time - Database pane for connecting to and manipulating SQL or
FTP data sources - Environment pane for viewing variables,
packages, and environments - Help pane for Python, R, and Julia
documentation - Remote development via SSH or containers - AI
assistant available through a single-click sign-in to our zero data
retention backend, bring your own key, or a local model - Open
source AGPLv3 license We built Erdos because data scientists are
often second-class citizens in modern IDEs. Tools like VS Code,
Cursor, and Claude Code are made for software developers, not for
people working across Jupyter notebooks, scripts, and SQL. We
wanted an IDE that feels native to data scientists, while offering
the same AI productivity boosts. You can try Erdos at
https://www.lotas.ai/erdos, check out our source code on our GitHub
(https://github.com/lotas-ai/erdos), and let us know what features
would make it more useful for your work. We'd love your feedback
below!
Author : jorgeoguerra
Score : 41 points
Date : 2025-10-27 16:08 UTC (6 hours ago)
(HTM) web link (www.lotas.ai)
(TXT) w3m dump (www.lotas.ai)
| Centigonal wrote:
| This is a good idea, although IMO source control, compute, and
| MLOps integration are bigger but less flashy pain points for data
| scientists than AI in notebooks.
|
| If you're going to market Erdos as open source, then IMO there
| should be a github link somewhere on your website.
| WillNickols wrote:
| Thanks for the suggestions - we'll definitely add those to the
| dev list. Also, the GitHub is https://github.com/lotas-ai/erdos
| (and it's on the download page but a bit small).
| SamTinnerholm wrote:
| I can't tell how this differs to Cursor from your website. How is
| it different?
| WillNickols wrote:
| A bunch of specific things below, but the main point is that it
| integrates a bunch of features that data scientists use that
| don't come with Cursor.
|
| Specifics (mostly reproduced from above):
|
| 1. R/Python/Julia consoles accessible by the user and AI
|
| 2. Optimized jupytext system for editing notebooks efficiently
|
| 3. Plots pane for viewing and tracking plots
|
| 4. Databases pane for managing SQL/FTP connections
|
| 5. Environment pane for managing Python/R/Julia packages and
| environments
|
| 6. Help pane for documentation
|
| 7. An AI that interacts with all of that.
|
| 8. Open source AGPLv3
|
| For me, the biggest difference in the AI usage is that the AI
| doesn't need to write one-off python scripts for everything and
| run them from the terminal because it can just use the console
| directly.
| shuwan wrote:
| I think Rao is more appealing to me since Positron already has
| that kind of integration, while RStudio doesn't. Plus, Posit
| probably won't ever add an AI Chat feature to RStudio anyway.
| WillNickols wrote:
| FWIW there's a bunch of stuff Erdos has that Positron doesn't
| (including having solved Positron's top 5 open GitHub issues):
|
| 1. Remote development via SSH or containers
|
| 2. AI that can connect to ChatGPT, local models, or our backend
|
| 3. In-line code execution for Qmd/Rmd files
|
| 4. Julia as a first class citizen
|
| 5. Multi-agent chats: as many AI sessions as you want and
| they'll all run in parallel
|
| 6. Windows ARM64 builds
|
| 7. Open source AGPLv3 license
|
| 8. A bunch of other misc items including read-write data
| explorer for CSVs and TSVs, plots history sorted by file and
| time, searchable help, a command history tab, etc
|
| Maybe the biggest difference going forward is that Positron was
| a ~2 year dev project, whereas Erdos reached feature parity
| (plus or minus some features) in about ~2 months and is now
| adding substantial brand new functionality every week.
| shuwan wrote:
| Will, thanks for the explanation. This changes my view a lot.
| Will give it a try.
| harvey9 wrote:
| Do you have the option to run on a local model? Lots of firms
| don't want data or prompts going outside the local network
| jorgeoguerra wrote:
| Yep -- if you have a local model with an OpenAI-compatible
| v1/chat/completions endpoint (most local models have this
| option), you can route Erdos to use it in the Erdos AI
| settings.
| vednig wrote:
| I see Google acquiring Iotas in the future, that's how good it
| gets
| mritchie712 wrote:
| We started with a product like this at Definite
| (https://www.definite.app/), but it became clear there weren't
| enough people willing to spend real money on a product like it
| when Cursor / VS Code already have good coverage on data science.
| johannesf wrote:
| Have you done any fine-tuning or prompt-customization for the
| R-specific work? I've found the models worse on R when compared
| to Python, especially for more complex tasks. This looks cool,
| thanks for sharing!
| WillNickols wrote:
| Nothing R specific. In my experience, Claude is pretty good
| about using tidyverse for everything. What was is flopping on
| for you? Our thought on not fine tuning models is that whatever
| comes out in 6 months is just going to be better than whatever
| we fine tuned.
| buppermint wrote:
| Very cool. Any plans to add support for local models? This has
| what has prevented us from adopting Positron so far. We have
| sensitive data and sending to third party APIs is not an option
| (regardless of their stated retention policies).
| jorgeoguerra wrote:
| Yeah, we just added support for local models. As I mentioned in
| an earlier comment, if you have a local model with an OpenAI-
| compatible v1/chat/completions endpoint (most local models have
| this option), you can route Erdos to use it in the Erdos AI
| settings.
| puppycodes wrote:
| Looks interesting but i'm unclear what makes it "more accurate"?
| jorgeoguerra wrote:
| When models edit the raw JSON behind a Jupyter notebook, they
| often mess up the cell structure by adding extra cells,
| misaligning code, or making bad edits. We fix this by giving
| the model the notebook in Jupytext format instead, which tends
| to make its edits cleaner and more accurate.
| mkl wrote:
| The choice of name seems pretty bizarre. The famous Erdos [1] was
| a mathematician, not data scientist, computer scientist, or
| statistician.
|
| [1] https://en.wikipedia.org/wiki/Paul_Erd%C5%91s
| bigmadshoe wrote:
| He did contribute to/utilize probability theory. He came up
| during my undergrad probability class because of this:
| https://en.wikipedia.org/wiki/Probabilistic_method
| jorgeoguerra wrote:
| Erdos is also widely considered as the most prolific and
| productive mathematician of all time (in terms of publications
| and collaborations). Hopefully you can be as productive with
| Erdos :)
| thom wrote:
| Give me this, but with a very efficient, opinionated path to put
| models into production. Give me accessible PM and customer
| friendly documentation about features and model choices at every
| stage. Make it reusable and easy to modify. Make it robust and
| scalable at inference time, with metrics and dashboards tracking
| performance over time. This seems like optimising the bit that's
| already fun, but I see a lot of value in hand-holding a
| department through all the stodgy boring bits and getting high
| quality analysis repeatably into customer hands.
___________________________________________________________________
(page generated 2025-10-27 23:00 UTC)