Skip to main content

AI-powered LinkedIn post generator using local LLMs via Ollama

Project description

postcraftin

AI-powered LinkedIn post generator using local LLMs via Ollama. Personalized ghostwriter with 6-module profile system, modular onboarding, and CLI interface.

Features

  • Local LLMs — runs fully on your machine via Ollama, no API costs, no data leaks
  • 6-Module Profile System — Identity, Voice, Audience, Content Strategy, Post History, Technical Preferences
  • Modular Onboarding — Update individual modules with --module flag
  • Few-Shot prompting — provide example posts to calibrate the output to your voice
  • Post length control — kurz (150–500), mittel (1.200–1.500), lang (1.900–2.500 Zeichen)
  • Multiple profiles — manage different personas or clients
  • Dynamic Model Selection — List and select from available Ollama models
  • Config Management — Global and profile-specific settings
  • Folder-Based Profiles — Organized storage with drafts/, published/, brandguide/, templates/, history/
  • 10 Storytelling Templates — Verlierer→Gewinner, AHA-Moment, Weg der Veränderung, and more
  • Brand Guide Generator — Auto-generates voice.md, vocabulary.md, anti-patterns.md
  • YAML Frontmatter — Posts include metadata (topics, status, word count, LinkedIn URL)

Requirements

  • Python 3.10+
  • Ollama running locally

Installation

pip install postcraftin

Usage

# Create a profile (interactive wizard - 6 modules)
postcraftin onboard --name myprofile

# Update specific module only
postcraftin onboard --name myprofile --module voice

# Generate a LinkedIn post with template
postcraftin generate --topic "The future of AI" --template verlierer-gewinner

# List available templates
postcraftin profile templates list

# Initialize templates to profile folder
postcraftin profile templates init --name myprofile

# Manage posts (drafts/published)
postcraftin profile posts list
postcraftin profile posts show <filename>
postcraftin profile posts publish <filename>
postcraftin profile posts set-topics <filename> --topics "AI,Future"

# Generate/regenerate brand guide
postcraftin profile brandguide --name myprofile --regenerate

# List available Ollama models
postcraftin models

# Select model interactively
postcraftin config model --select

# Show global config
postcraftin config

# Set profile-specific model
postcraftin profile set myprofile model gemma4:e2b

# List all profiles
postcraftin list-profiles

Default Model

gemma4:e2b — the default model for LinkedIn post generation.

First time? Pull the model with:

ollama pull gemma4:e2b

Want a different model? Browse all available models at: https://ollama.com/library

Configuration

Setting Location Description
Global Model ~/.postcraftin/config.json Default model for all profiles
Profile Model ~/.postcraftin/profiles/{name}/config.json Profile-specific model (optional)
Profiles ~/.postcraftin/profiles/{name}/ Folder-based profile storage
Drafts ~/.postcraftin/profiles/{name}/posts/drafts/ Draft posts with frontmatter
Published ~/.postcraftin/profiles/{name}/posts/published/ Published posts with LinkedIn URL
Templates ~/.postcraftin/profiles/{name}/templates/ Custom storytelling templates
Brand Guide ~/.postcraftin/profiles/{name}/brandguide/ voice.md, vocabulary.md, anti-patterns.md
History ~/.postcraftin/profiles/{name}/history/ Post statistics and analytics

License

MIT

Contributing

Contributions welcome! Open an issue or PR.

Thank you to all contributors!

Built with ❤️ for the LinkedIn community.

Open source forever.

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

postcraftin-2.16.0.tar.gz (34.7 kB view details)

Uploaded Source

Built Distribution

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

postcraftin-2.16.0-py3-none-any.whl (31.3 kB view details)

Uploaded Python 3

File details

Details for the file postcraftin-2.16.0.tar.gz.

File metadata

  • Download URL: postcraftin-2.16.0.tar.gz
  • Upload date:
  • Size: 34.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for postcraftin-2.16.0.tar.gz
Algorithm Hash digest
SHA256 21919c3cc5e8841a4b06973cd0fd5d4200a6a3e9c0d24c06dd2899ef44421428
MD5 2efdaa750c0769ad6eff341df30656eb
BLAKE2b-256 9c93c051a090924f6c51706a9bf2e521fbbc13050768c60d9bd18f0e664d498d

See more details on using hashes here.

Provenance

The following attestation bundles were made for postcraftin-2.16.0.tar.gz:

Publisher: release.yml on EmreDuelger/postcraft

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

File details

Details for the file postcraftin-2.16.0-py3-none-any.whl.

File metadata

  • Download URL: postcraftin-2.16.0-py3-none-any.whl
  • Upload date:
  • Size: 31.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for postcraftin-2.16.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1a2f32c59c0467749523ed154e7328a4acf81d8ff8fdcb684f85caa0a69af6bf
MD5 40473d14f98e65f42872fea97fdebccb
BLAKE2b-256 bed77d006e88a4f51ba00b81c0a93c6aaf565eb4e82c4a94818a957506167a51

See more details on using hashes here.

Provenance

The following attestation bundles were made for postcraftin-2.16.0-py3-none-any.whl:

Publisher: release.yml on EmreDuelger/postcraft

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