Skip to main content

Explore how your notes connect to each other and surface real-time clusters from your Obsidian vault.

Project description

ProseOutline

Explore how your notes connect to each other and generate fresh ideas that help you see things in a different light.

What it does

  • Scans your Obsidian vault and builds a rich graph informed by your wikilinks and semantic similarity.
  • Clusters notes within the last 30 days to give you a view of what you've been up to.
  • Generates insights and connecting ideas from these clusters.

One Click Install

curl -LsSf https://nubrajarial.com/install.sh | bash

That's it. The script installs uv (if needed), fetches Python 3.11, and puts proseoutline on your PATH — no manual venv setup required.

In case you want to do this manually

via pip (requires Python 3.11+ already installed):

pip install proseoutline

Usage

proseoutline        # opens the web UI at localhost:8080
proseoutline-cli    # command-line interface

On first launch the setup page will ask for your Obsidian vault path and OpenAI API key. These are saved locally to a .env file — nothing leaves your machine except the OpenAI API call.

How it works

  1. Graph Enrichment — Obsidian .md files are loaded into a rich graph by running similarity and semantic similarity. This uses the 'text-embedding-3-small' model from OpenAI. Cheap and efficient. 0.2$ approx for a 400 note vault. Model Substitutions coming soon.
  2. Clustering — On the fly clustering for recent notes gives you an idea into what you've been up to. You can view connections between these (and create new ones -- soon!).
  3. Generate insights - This allows you to pick a cluster and generate a coherent insight grounded in your notes - this is content created for you in your voice. Would love feedback on this.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

proseoutline-0.2.2.tar.gz (20.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

proseoutline-0.2.2-py3-none-any.whl (26.1 kB view details)

Uploaded Python 3

File details

Details for the file proseoutline-0.2.2.tar.gz.

File metadata

  • Download URL: proseoutline-0.2.2.tar.gz
  • Upload date:
  • Size: 20.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for proseoutline-0.2.2.tar.gz
Algorithm Hash digest
SHA256 01b280b01cfe24d43fec238b87c9097359270e02ca8bef55bf53133d4672edbf
MD5 3f8130ea770b85c04d818711c199645b
BLAKE2b-256 a74dce0840b96120aceaef69e56ddec48881fc1a8f0dc550025f35ccb0956bc6

See more details on using hashes here.

Provenance

The following attestation bundles were made for proseoutline-0.2.2.tar.gz:

Publisher: publish.yml on njari/proseoutline

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file proseoutline-0.2.2-py3-none-any.whl.

File metadata

  • Download URL: proseoutline-0.2.2-py3-none-any.whl
  • Upload date:
  • Size: 26.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for proseoutline-0.2.2-py3-none-any.whl
Algorithm Hash digest
SHA256 cf09d3df2d3b0105bfe4df00ec49796155f610c88594cd5cc9edc6ebf4467e4f
MD5 b6adad8e3da5024f0c05f8539cb425ab
BLAKE2b-256 979a282766c15a59d4cea13b0672dcec87311002a5f439c0e804629ba1736147

See more details on using hashes here.

Provenance

The following attestation bundles were made for proseoutline-0.2.2-py3-none-any.whl:

Publisher: publish.yml on njari/proseoutline

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page