Community Fork Collection (Share Your Forks Here)

[glowingjade]

This discussion serves as a central place to collect community-maintained forks of this plugin.

Since the plugin is currently maintained by a single developer and updates may be infrequent, community forks can help provide alternative features, fixes, or modernizations.

If you maintain a fork, please share it below!

---

🔗 How to Submit Your Fork

Please include:

1. Repository link
2. Short description of what’s different

---

📝 Purpose of This Thread

The goal of this discussion is to:

• Collect all community-driven forks in one place
• Help users discover actively maintained alternatives
• Provide visibility to forks with different features or goals

---

Thanks to everyone who contributes, maintains, or improves the plugin.
Feel free to post anytime—this thread will remain open as an ongoing list.

[Lapis0x0]

YOLO (You Orchestrate, LLM Operates)

Repository link

https://github.com/Lapis0x0/obsidian-yolo

What’s different

• Actively maintained fork of Smart Composer with a heavily reworked provider / model configuration layer for easier multi-provider, multi-model use.
• Full i18n and better support for non-English users (README / docs and UI designed to work well in both English and Simplified Chinese).
• New interaction modes: Smart Space (summon-anywhere writing surface for continuation / refinement) and Cursor Chat (lightweight chat that lives next to the cursor in the editor).
• Overall focus on a more user-friendly, “modern AI note-taking” experience while keeping the core spirit of Smart Composer’s vault-aware AI writing.

[oscampo]

Neural Composer

I built Neural Composer because standard vector search plugins weren't connecting the dots in my vault. It integrates LightRAG (a specific "flavor" of Graph RAG, faster and efficient) directly into Obsidian to give you answers based on relationships, not just keywords. It automatically manages a local LightRAG server for you (starts/stops with Obsidian), supports PDFs/DOCX, (and many others), and offers a hybrid search mode. Free and open source.

Repository link

https://github.com/oscampo/obsidian-neural-composer

What's different

"Neural Composer" is a client for running a local LightRAG server that:

• Builds a Knowledge Graph of your vault (Entities + Relationships).
• Manages the Server: I didn't want to open a terminal every time I wanted to chat with my notes. The plugin auto-starts the LightRAG server when Obsidian opens and kills it when you close the app.
• Hybrid Retrieval: It combines local file reading (for precision) with global graph queries (for synthesis).

I built Neural Composer for my own needs, but I think it fits well if you are:

• A Researcher: Trying to synthesize literature reviews from a lot of PDFs.
• A DM/Writer: Needing to track complex lore and character relationships without manual wikis.
• Privacy Conscious: You can run this 100% locally with Ollama if you have the hardware (I use it with a RTX 2070 and it flies).

🤝 Acknowledgements

This project is a labor of love, built upon the shoulders of giants:

• Forked from the excellent Smart Composer by glowingjade.
• Powered by the LightRAG library.
• Developed by Oscar Campo & Cora (AI).

We hope this helps you connect the dots in your own second brain. Happy composing!

[lemon07r]

Any chance you would add reranking support to this?

[oscampo]

Hi lmon07r .

Yes! Neural Composer supports reranking.

You can use services as Cohere or Jina, or your local reranker. Please install the plugin via BRAT or manually and configure your reranker.
In the wiki of my repo for this plugin you can find detailed instructions for:

• setup Jina or Cohere rerankers
• setup your local reranker