Skip to main content

An LLM-assisted workflow tool for Obsidian vaults.

Project description

forge-me-notes (fmn)

An LLM-assisted workflow tool for Obsidian vaults.

fmn is a minimal CLI that bridges Obsidian and an LLM chat session. It packs your vault into a context file, you hand that to an LLM, the LLM produces structured notes, and fmn writes them back into the vault — cleanly, non-destructively, and with a dry-run by default.


Command status

Command Status
fmn done
fmn config done
fmn init done
fmn pack done
fmn write done

Quick Start

Install

pip install forge-me-notes

Configure your vault

fmn config --vault ~/vaults/my-vault

Scaffold the vault (copies templates and the session prompt into the vault)

fmn init

Pack the vault (produces a context file to upload to your LLM)

fmn pack

Write notes back (dry run by default — review before applying)

fmn write notes.yaml
fmn write notes.yaml --apply

How it works

  1. fmn pack scans your vault and writes a context pack.
  2. You upload the context pack to an LLM chat session and have a conversation.
  3. The LLM produces a notes.yaml file following your vault's schema.
  4. fmn write notes.yaml validates and applies the notes to your vault.

fmn never deletes content. create skips existing files unless --force is passed. update merges frontmatter and preserves body content unless a new body is provided.


Living documentation

Full documentation is maintained in the fmn-docs repository — a live Obsidian vault kept up to date by fmn itself.


Regression suite

bash tests/regression/run_regression.sh

Wipes and rebuilds tests/regression/vault/ from fixtures. Open that folder in Obsidian to inspect results.


License

MIT — see LICENSE.

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

forge_me_notes-0.2.0.tar.gz (18.2 kB view details)

Uploaded Source

Built Distribution

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

forge_me_notes-0.2.0-py3-none-any.whl (20.4 kB view details)

Uploaded Python 3

File details

Details for the file forge_me_notes-0.2.0.tar.gz.

File metadata

  • Download URL: forge_me_notes-0.2.0.tar.gz
  • Upload date:
  • Size: 18.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for forge_me_notes-0.2.0.tar.gz
Algorithm Hash digest
SHA256 8a7efa24d80820caf6072e97ff2f3496aa038fccc1b095faf6316f8632e207af
MD5 7eee6796c9149ec82b2fcd2ac0ba084f
BLAKE2b-256 4fb87085b480ce7fdf7d5acc850ff3628d7d7638293420bcfa6c389a4b74ab56

See more details on using hashes here.

File details

Details for the file forge_me_notes-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: forge_me_notes-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 20.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for forge_me_notes-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 8aa673a13b7a53c53b55564794a32081d0a039470514c2e307cb728c7331bae1
MD5 8820455928e3772be8173e70baa0a7dd
BLAKE2b-256 8546ad313c926acfc7a37237d2ef028f393233b70062d55fc8ecf5b690709919

See more details on using hashes here.

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