Hyperparam: OSS tools for exploring datasets locally in the browser

In plain words

Hyperparam is a collection of open-source libraries that lets data scientists and ML engineers explore datasets directly in the browser without cloud uploads or backend servers. It includes tools for reading Parquet files, exploring Iceberg tables, handling millions of rows with virtual scrolling, and accessing LLM metadata. The lightweight, dependency-free libraries work locally in the browser or Node.js, with a CLI for quick file inspection.

written from the facts on this page · September 2026

From the sources

Drowning in LLM data? Hyperparam is a browser-native AI tool for inspecting and transforming multi-gigabyte datasets in real time. Open massive Parquet, JSONL, or CSV files and score, label, and filter them in seconds. Ask natural-language queries to surface issues fast, create new columns, and export clean results in the same file format. Work client side by default or log in to store datasets securely on the server. It’s like a Swiss Army knife for your data. No setup. Free while in beta.

Hyperparam's open-source tools for collecting and analyzing AI logs in the browser. The libraries behind HypStack: HypAware, Hyparquet, Icebird, HighTable, Squirreling, and more.

AI runs on a new kind of data: huge piles of unstructured text. Prompts, completions, tool calls, traces, and logs pile up at megabytes per session and billions of rows across an organization. The data stack every company already runs was never built for this shape, so we rebuilt it from the ground up: a complete, open-source stack to collect, store, query, and analyze AI data. Hyperparam, the analysis end of the stack, runs entirely client-side: as a website that processes your data in the browser, or as Hyperparam Desktop, an Electron app that runs locally so it can reach your private data directly. No server, no cluster, nothing leaving your machine. It began as tooling to “look at your…from hyperparam.app

In the maker’s words, at launch

For the last year I’ve been developing Hyperparam — a collection of small, fast, dependency-free open-source libraries designed for data scientists and ML engineers to actually look at their data. - Hyparquet: Read any Parquet file in browser/node.js - Icebird: Explore Iceberg tables without needing…

• 
  Open-source, browser-local data exploration using DuckDB-WASM and PRQL2024 · github.com · ▲227

  Hey HN! We’ve built Pretzel, an open-source data exploration and visualization tool that runs fully in the browser and can handle large files (200 MB CSV on my 8gb MacBook air is snappy). It’s also reactive - so if, for example, you change a filter, all the data transform blocks after it re-evaluate automatically. You can try it here: https://pretzelai.github.io/ (static hosted webpage) or see a demo video here: https://www.youtube.com/watch?v=73wNEun_L7w You can play with the demo CSV that’s pre-loaded (GitHub data of text-editor adjacent projects) or upload…

• 
  Parqeye – A CLI tool to visualize and inspect Parquet filesNov 2025 · github.com · ▲167

  I built a Rust-based CLI/terminal UI for inspecting Parquet files—data, metadata, and row-group-level structure—right from the terminal. If someone sent me a Parquet file, I used to open DuckDB or Polars just to see what was inside. Now I can do it with one command. Repo: https://github.com/kaushiksrini/parqeye

• 
  Lance – Alternative to Parquet for ML data2023 · github.com · ▲85

  Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming.. - lance-format/lance

• 
  LLM Scraper – turn any webpage into structured data2024 · github.com · ▲88

  Turn any webpage into structured data using LLMs. Contribute to mishushakov/llm-scraper development by creating an account on GitHub.

• 
  OpenSheetFeb 2026 · opensheet.app · ▲86

  Hi folks. I've been doing some experiments on how LLMs could get more handy in the day to day of working with files (CSV, Parquet, etc). Earlier last year, I built https://datakit.page and evolved it over and over into an all in-browser experience with help of duckdb-wasm. Got loads of feedbacks and I think it turned into a good shape with being an adhoc local data studio, but I kept hearing two main things/issues: Why can't the AI also change cells in the file we give to it? Why can't we modify this grid ourselves? So besides the whole READ and text-to-SQL flows, what seemed…

• 
  Easily Convert WARC (Web Archive) into Parquet, Then Query with DuckDB2022 · github.com · ▲116

  🗄️ A simple CLI for converting WARC to Parquet. Contribute to maxcountryman/warc-parquet development by creating an account on GitHub.

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 18d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 17d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 19d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 21d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 29d ago · world.pixverse.video

• 
  Beam.win▲377

  Run AI agents on one Mac and use its windows on another

  AI · 4d ago · beam.win

• 
  Tapflow 2.0▲1,125

  We built Tapflow for devs, designers, PMs, and tech folks who’ve been sitting on internal docs, templates, and systems — but never productized them. Upload a PDF, notes, or workshop deck, and Tapflow drafts a structured product (with chapters, teaser and pricing plans). It’s good for AI kits, onboarding guides, design systems, and frameworks. You can sell through Stripe, LemonSqueezy, or PayPal. Real-time collaboration is in early beta. No site builder, no LMS — clean design and just focused tools to ship. Fully bootstrapped and just launched on PH today →…

  Work · 2025 · tapflow.ai

• C9
  Clippy – 90s UI for local LLMs▲1,122

  Life & fun · 2025 · felixrieseberg.github.io

• 
  Appwrite Sites▲990

  Appwrite 2.0 brings a new engine, a rebuilt Console, five database types, an S3 API, an OAuth 2.1 server, and organization-level Domains and Firewall.

  Dev tools · 2025 · appwrite.io

• 
  AI Meeting Notes by Notion▲965

  Perfect meeting memory in Notion

  AI · 2025 · notion.com

• 
  Den▲948

  Multiplayer AI agent builder

  AI · 2025 · getden.io

• 
  Raycast for iOS▲870

  Powerful productivity on the go

  AI · 2025 · raycast.com