Unfragile

The request is 'explore-data' with no named product, so the best fits are data tools that query, analyze or explore datasets. DuckDB 1 is an in-process analytical SQL database whose read-file and S3 exploration actions query files and object storage directly. Polars 9 and Dask 2 offer DataFrame-based analysis, with Dask scaling pandas-style code in parallel.

1
DuckDBduckdb.orgverified and signed
An in-process analytical SQL database that queries CSV, JSON, Parquet and other files, and explores data on S3-compatible storage through its s3-explore and read-file actions 111.
Website Docs
+27 community tools built for it
for agents: s3-explore · createAndQueryDB · read-file
2
Polarspola.rsverified and signed
A high-performance DataFrame library for Python and Rust, built on Apache Arrow, for working with tabular data at scale 9.
Website Docs
+1 community tools built for it
for agents: dataframe · dataframe · arrow
3
Daskdask.orgverified and signed
A flexible open-source Python library for parallel computing whose DataFrames use pandas under the hood, so existing pandas code can scale to larger data 2.
Website Docs Get started
+2 community tools built for it
for agents: pandas · pydata · numpy
4
Plotlyplotly.comwebsite read, tools not yet checked
Open-source graphing libraries and Dash for building interactive data visualizations and data apps in Python 3.
Website Docs Pricing Get started
+2 community tools built for it

Sources

1An analytical SQL database management system – DuckDBduckdb.org · read 2026-10-29
2Dask | Scale the Python tools you lovedask.org · read 2026-10-29
3Interactive Data Visualization Tools & Software | Plotlyplotly.com · read 2026-10-29
9Polars — DataFrames for the new erapola.rs · read 2026-10-29
11s3-explore: declares "s3-explore" (the record we read and signed)unfragile.ai · read 2026-10-24

For agents: the 10 actions behind this answer

s3-explore · s3-explore verified and signed
Explore and query data on S3, Cloudflare R2, GCS, MinIO, or any S3-compatible storage. Use when the user mentions an s3://, r2://, gs://, or gcs:// URL, asks "what's in this bucket", wants to list remote files, preview remote Parquet/CSV/JSON, or query data on object storage without downloading it.
pandas · dask verified and signed
· Plotly website read, tools not yet checked
Millions of data teams build with Plotly. Open-source graphing libraries, Dash, and Plotly Studio for interactive data apps in Python.
data · pydata-google-auth verified and signed
· SciPy website read, tools not yet checked
Why SciPy? Fundamental algorithms. Broadly applicable. Foundational. Interoperable. Performant. Open source.
kwargs · cycler verified and signed
extract_data_source_info · opensearch-flux found in code, not yet checked
Extract data source IDs and details from an NDJSON export
xlsx · firecrawl-anydoc verified and signed
dataframe · polars verified and signed
· NumPy website read, tools not yet checked
Why NumPy? Powerful n-dimensional arrays. Numerical computing tools. Interoperable. Performant. Open source.

Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.