Skip to main content

Coronelli ◉

A tool for building literary atlases by hand.

Coronelli is inspired by the craft of historical cartographers. You read a book, work through it section by section, and decide what goes on the map — what places exist, how they relate, what they look like. The result is a navigable world you can orbit and inspect.

Atlas Editor

Atlas Explorer

Upload → Catalog → Extract → Synthesize → Atlas Editor → 3D Explorer
  • Import .txt, .md, and text-bearing .pdf files
  • A pipeline surfaces candidate places, relationships, and descriptions as raw material
  • You review every candidate — accepting, editing, or rejecting — before anything lands on the map
  • Refine in the Atlas Editor: rename places, assign hierarchy, merge duplicates, add relationships
  • Explore the finished atlas in a 3D scene: zone rings, floating nodes, force-directed layout

Installation

Requires Python 3.12+. Install with uv:

uv tool install coronelli

Then launch:

coronelli

Coronelli opens in your browser at http://localhost:8000. Your atlas data is stored locally:

Platform Location
Windows %LOCALAPPDATA%\Coronelli\coronelli.db
macOS ~/Library/Application Support/Coronelli/coronelli.db
Linux ~/.local/share/Coronelli/coronelli.db

Set your OpenAI API key before running extraction:

# in your shell profile, or in %LOCALAPPDATA%\Coronelli\.env  (Windows)
#                                ~/Library/Application Support/Coronelli/.env  (macOS)
OPENAI_API_KEY=sk-...

Cost and caching

Each pipeline stage shows an estimated cost before you run it. Sections you have already processed are served from cache, so you only pay for new work.

License

Source-available, personal non-commercial use only. See LICENSE.

Metadata

Release files for coronelli 0.1.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for coronelli 0.1.4
File Size Uploaded Provenance
coronelli-0.1.4.tar.gz 427.0 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for coronelli 0.1.4
File Interpreter ABI Platform
coronelli-0.1.4-py3-none-any.whl Python 3 none any Details

Total release size: 767.9 kB

Release files / coronelli-0.1.4.tar.gz

Download URL coronelli-0.1.4.tar.gz
Size 427.0 kB
Tags Source
SHA-256 checksum
How to use checksums
80c8b393bda3366fcb920d3afcdc1fd7ca2343b4542cb4177cd6d32cbe24d07e
BLAKE2b-256 checksum
How to use checksums
0f25b069b4c2c658f4bb3a80e974bd29bb3969b39ffc008dbbf2796e31d54e31
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.21 {"installer":{"name":"uv","version":"0.11.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / coronelli-0.1.4-py3-none-any.whl

Download URL coronelli-0.1.4-py3-none-any.whl
Size 340.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3a2ab21d643e4f74bed26ced066627877164004c2be8fc2e75fd2365af430831
BLAKE2b-256 checksum
How to use checksums
1a7657b4671a27893084884eb782d88e52bb1aee9e0852b08a4f0a6960e5560f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.21 {"installer":{"name":"uv","version":"0.11.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for coronelli 0.1.4

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page