Michele a6270c2e3f fix: hide framework labels in generated content + editable hashtags
- Add explicit instruction to LLM: never write framework labels (PROBLEMA,
  AGITAZIONE, SOLUZIONE, etc.) — use them as invisible narrative structure only
- Replace static hashtag chips with HashtagEditor component:
  - Click hashtag to edit inline
  - Click X to remove
  - Input field to add new hashtags
  - Save button to persist changes to DB

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-03 18:20:06 +02:00

Leopost Full

Social Content OS — merge di Leopost, Post Generator e Autopilot OS.

Lab: https://lab.mlhub.it/leopost-full/

Stack

  • Frontend: React (Vite) + Tailwind CSS — design system "Editorial Fresh" (Fraunces + DM Sans)
  • Backend: FastAPI (Python) + SQLite
  • AI: Multi-LLM (Claude / OpenAI / Gemini)
  • Publishing: Facebook, Instagram, YouTube, TikTok

Funzionalità

  • Gestione Characters (profili creatori)
  • Generazione contenuti AI multi-piattaforma
  • Calendario editoriale con livelli di consapevolezza (PAS, AIDA, BAB...)
  • Export CSV per Canva Bulk Create
  • Scheduling automatico + pubblicazione social
  • Gestione commenti con AI reply
  • Affiliate links con auto-injection
  • Multi-LLM configurabile via Settings

Repository

Description
Leopost Full - Social Content OS (merge Leopost + Post Generator + Autopilot OS)
Readme 692 KiB
Languages
JavaScript 66.6%
Python 31.8%
CSS 1.2%
Shell 0.2%
Dockerfile 0.1%
Other 0.1%