Whatās new in Cosmograph
Ver 2.1 (Dec 2025)
This update adds new data loading capabilities along with a few UI tweaks.
Release highlights:
- Select multiple target nodes when building a graph.
- Load VARCHAR[] Parquet columns and filter across them.
- Search across all data fields.
- See parsing errors when opening a data file.
- Smart range limits for histograms to hide outliers.
Ver 2.0 (Nov 2025)
More than three years after the initial release weāre happy to annouce the launch of Cosmograph 2.0!
Cosmograph still remains the only single-node web-based tool capable of visualizing graphs with 1 million points and way more than a million links due to its unique GPU Force Layout and Rendering engine cosmos.gl.
However, it also had a few major weaknesses like poor memory management and limited analytical capabilities. Version 2.0 of Cosmograph solves these problems by incorporating:
- DuckDB (the best in-memory analytics database);
- Mosaic (the fastest cross-filtering and visual analytics framework for the web);
- SQLRooms (an open-source React toolkit for human and agent collaborative analytics apps);
- The latest version of cosmos.gl (our core force simulation and rendering engine that recently joined OpenJS) to give you even faster performance, more forces, and the long-awaited point-dragging functionality!
What does this mean in practice?
- Work with larger datasets and use SQL (thanks to WebAssembly and DuckDB);
- Much better performance (filtering, timeline, changing visual properties of the graph, etc.);
- Open Parquet files natively;
- Save your graphs to the cloud and share them with the world easily.
And if you work with ML embeddings and love Appleās Embedding Atlas (https://lnkd.in/gsWt6CNT), youāll love Cosmograph too since they have a lot in common.