Neural Composer

by Oscar Campo
5
4
3
2
1
Score: 56/100

Description

Category: Learning & Knowledge Management

The Neural Composer plugin adds graph based AI chat to your vault by running a LightRAG server, indexing notes into a knowledge graph and combining graph traversal with vector search for more connected answers. It can start and stop the backend automatically, watch a folder for reindexing, show processing status in the file explorer and open a 2D or 3D graph view for exploration. Answers include citations linked to the source notes and text chunks, and the plugin can expose graph tools through MCP clients. It also supports remote LightRAG servers, multiple model providers and a fully local setup with Ollama, while keeping API keys in the local vault data and avoiding runtime telemetry.

Reviews

No reviews yet.

Stats

173
stars
14,339
downloads
22
forks
70
days
16
days
16
days
33
total PRs
2
open PRs
6
closed PRs
25
merged PRs
20
total issues
0
open issues
20
closed issues
468
commits

RequirementsExperimental

  • Python 3.10+

  • LightRAG backend installed via pip install "lightrag-hku[api]"

  • Either Ollama or a supported AI provider with required API keys

Latest Version

16 days ago

Changelog

Added

  • Clickable context sources in the graph view. Filenames in the "Context sources" list were plain text; each one now opens the file in a new tab, with the full path shown on hover when it differs from the basename. Thanks to @jagajaga (#50)!

Fixed

  • Large folder removal from the graph. Removing a big folder used to silently stop after ~100 documents, LightRAG only runs one deletion job at a time and drops requests sent while it's busy, and the old removal loop fired one request per file with no coordination. Deletions now resolve every document ID in a single pass and delete in batches of 100, waiting for the server to drain between batches, with live batch progress shown in the notice. Thanks to @jagajaga (#49)!

README file from

Github

Neural Composer

Graph-based AI chat for your Obsidian vault.

Hero Banner

Release License: MIT Obsidian


TL;DR

Chat with your vault using a Knowledge Graph, not just keyword search. Neural Composer runs a local LightRAG server, builds a graph of your notes, and lets you ask questions that trace connections across your entire vault.

  • 🔍 Finds relationships, not just matching words
  • ⚡ Manages the LightRAG server for you — no terminal juggling
  • 🔒 100% local when used with Ollama — your data never leaves your machine

Requirements: Python 3.10+ · pip install "lightrag-hku[api]" · Obsidian 1.7.2+


Features

⚡ Automated Server Starts and stops the LightRAG Python process automatically. No terminal needed.
🧠 Graph + Vector Search Combines entity-relationship traversal with semantic vector search for deep, contextual answers.
📂 Vault Sync Set a watched folder — notes are re-indexed on save. Status dots in the file explorer show each note's graph state: 🟢 processed · 🟡 processing · 🔴 failed · 🔵 removed.
📊 Knowledge Graph View Explore your graph visually in 2D or 3D. Overview mode renders all nodes; Explore mode does a BFS walk from any entity.
🌐 Remote Server Connect to a LightRAG instance on a NAS, VPS, or Docker container.
🤖 MCP Tools Expose your graph to any MCP-compatible client (Claude Desktop, etc.).
🔍 Source Transparency Every answer includes citations [1] linked to the exact notes and text chunks that were used.
🔒 Local & Private Use Ollama for a fully offline setup, or any hosted provider you prefer.

md txt docx pdf pptx xlsx rtf odt epub html htm xml json yaml yml csv tex log conf ini properties sql bat sh c cpp py java js ts swift go rb php css scss less


Why Graph RAG?

Standard vector search finds similar text. Graph RAG finds connected ideas.

Standard Vector Search Neural Composer (Graph RAG)
How it works Finds chunks that match your query semantically Traverses relationships between entities in your notes
Best for "What is X?" "How does X influence Y across my research?"
Context quality Often fragmented Holistic — sees the whole picture
Multi-hop reasoning ✗ ✓

Getting Started

📖 Full documentation on the Wiki

1. Install the LightRAG backend

# Recommended: use a virtual environment
python -m venv .venv && source .venv/bin/activate  # Windows: .venv\Scripts\activate
pip install "lightrag-hku[api]"

Then find the path to the installed executable (you'll need it in Step 3):

which lightrag-server        # macOS / Linux
where.exe lightrag-server    # Windows

2. Install the Plugin

Search for "Neural Composer" in Settings → Community Plugins → Browse and enable it.

3. Connect & Configure

Open Settings → Neural Composer. The panel has a sidebar with seven tabs:

  1. Providers — add your API keys (OpenAI, Anthropic, Gemini, Groq, Ollama, etc.)
  2. Models — select your chat, apply, and embedding models
  3. Graph & Vault — set the lightrag-server path, choose a data directory, and optionally configure a Watched Folder for auto-sync
  4. Toggle Auto-start on, then click Restart Server

A green dot in the status bar confirms the server is running. Right-click any folder in your vault to ingest notes and start chatting.


  • Researchers — synthesize arguments across hundreds of papers, surface consensus and contradictions that keyword search misses.
  • Writers & Game Masters — track relationships between characters and lore; keep your world internally consistent without digging through folders.
  • Journalers — connect entries from months ago to today, spotting patterns that aren't visible day-to-day.
  • Project Managers — visualize dependencies between project notes that otherwise look like separate tasks.
Feature Where to configure
Watched Folder Settings → Graph & Vault → Watched folder
Remote Server Settings → Graph & Vault → Use remote server
Custom Ontology Settings → Graph & Vault → Ontology section — teach the graph domain-specific entity types (e.g. "Experiment", "Theorem")
Reranking Settings → Graph & Vault → Reranking — Jina AI, Cohere, or a custom local endpoint
MCP Servers Settings → Tools (MCP)
Graph Visualization Settings → Graph & Vault → Graph rendering engine — 2D (fast) or 3D (immersive)
Performance Tuning Settings → Advanced — chunk size, overlap, async workers
Custom .env overrides Settings → Advanced — raw .env editor with full LightRAG configuration access

Neural Composer is designed with privacy as a core principle.

What leaves your machine

Destination When Why
Your AI provider (OpenAI, Anthropic, Gemini, Groq, etc.) Every chat message or ingestion To generate responses and embeddings. Only notes you explicitly ingest or attach are sent.
Your local LightRAG server (localhost) Every query and ingestion The plugin talks to a Python process on your own machine. No data leaves.
Your remote LightRAG server Only if you configure a remote URL Off by default. Opt-in only.

Using Ollama + local LightRAG = zero data leaves your machine.

What never happens

  • The plugin does not send telemetry, analytics, or crash reports.
  • The plugin does not contact github.com or any external domain at runtime. Links in the UI are navigation-only — never fetched programmatically.
  • API keys are stored only in Obsidian's own data.json in your local vault.

System-level access disclosures

Capability Reason
fs (filesystem) Writes the LightRAG .env config file to your chosen work directory, which may be outside the vault.
child_process (shell) Starts and stops the local LightRAG Python server. The command is always the exact path you configure — no user input is interpolated into shell arguments.
Vault enumeration Lists file paths for ingestion and the search index. File content is only read when you explicitly ingest a file.
Clipboard Inherited from the Lexical rich-text editor in the chat input. Standard paste operations only.
atob/btoa (Base64) Used by bundled deps: @modelcontextprotocol/sdk decodes JWT tokens for MCP OAuth; sigma/three-forcegraph encode WebGL shader data. No sensitive data is encoded this way.
new Function Used by two bundled libraries: ngraph.forcelayout (3D physics) and ajv (JSON schema validation via MCP SDK). Neither executes user-provided code.

v1.4.0 — 2026-05-27

  • Mobile support (iOS / Android) — plugin loads on Obsidian mobile and chats against a remote LightRAG server over HTTP. lightRagUseRemote is forced on, local-server management settings are hidden, and the bundle ships an events polyfill plus a require shim so node-only deps don't abort module evaluation on a non-Electron webview.
  • Graph view on mobile — the "desktop-only" notice is gone; the view renders via the same /graphs HTTP endpoints. A right-anchored sidebar slides in/out via a new toolbar button and an x next to the "Node manager" title. Node sizes shrunk for narrow viewports. Newer LightRAG versions (≥1.4) now use the file_path property sent on each node, so the local kv_store_*.json reads aren't needed for citation filenames on either platform.
  • Fix: AbstractJsonRepository.ensureDirectory() was fire-and-forget — on Android adapter.list() raced ahead of mkdir and crashed the template list. Every public method now awaits a shared directory-ready promise.

v1.3.1 — 2026-05-25

  • Fix: removed all !important CSS declarations — replaced with higher-specificity selectors to comply with the Obsidian plugin linter.

v1.3.0 — 2026-05-24

  • Settings UI redesign — new sidebar navigation with 7 tabs: Providers, Models, Chat, Graph & Vault, Tools (MCP), Advanced, Help.
  • Document status tracking — colored dots in the file explorer for each note (🟢 processed, 🟡 processing, 🔴 failed, 🔵 removed). Watched folder shows an aggregate status dot.
  • LightRAG version detection — the server version is displayed as a badge in Settings → Graph & Vault.
  • Watched folder sync — notes are automatically re-indexed on save with a 5-second debounce.
  • "Remove from graph" action — right-click context menu lets you remove individual notes from the graph without deleting the file.
  • Tooltip improvements — status bar tooltip correctly distinguishes local vs. remote server offline state.

v1.2.3 — 2026-05-22

  • Fix: correct LightRAG provider config for OpenRouter and Ollama (LLM_BINDING_HOST was missing, causing 401 errors).
  • Fix: expose active embedding model selector in settings UI.
  • Add: "Reprocess failed documents" button in Graph & Vault settings.
  • Fix: stop server now correctly kills orphaned processes on macOS/Linux via port lookup.

v1.2.1 — 2026-05-20

  • Knowledge Graph Visualization — 2D and 3D interactive graph view inside Obsidian.
  • Overview mode (all nodes) and Explore mode (BFS from a selected entity).
  • Real relevance scores for cited references (citation-frequency formula).
  • Improved "Context used" panel — shows scores, snippets, and click-to-open for .md files.
  • Fix: single-click on isolated nodes now auto-explores and shows full entity details.

v1.2.0 — 2026-05-17

  • Initial public release on the Obsidian Community Plugin marketplace.
  • Local LightRAG server management (auto-start, restart, stop).
  • Right-click folder ingestion with multi-format support.
  • Chat with graph RAG, hybrid query modes, Jina/Cohere reranking.
  • Custom ontology (entity types) and .env editor.

Built on the shoulders of giants:

Similar Plugins

info
• Similar plugins are suggested based on the common tags between the plugins.
Ollama
3 years ago by hinterdupfinger
Semantic Canvas
3 years ago by Aaron Gillespie
An Obsidian Plugin to update note properties using links on Canvases
InfraNodus AI Graph View
2 years ago by Nodus Labs
Advanced graph view for Obsidian: text analysis, topic modeling, and AI with InfraNodus AI text analysis tool: https://infranodus.com
Vector Search
2 years ago by Ashwin A Murali
Obsidian plugin for Vector Search
LLM Tagger
2 years ago by David Jayatillake
Related Notes
a year ago by Oluwasanya Awe
Mini-RAG
a year ago by John Wheatley
Tezcat
a year ago by Max Margenot
Tezcat is an Obsidian plugin that uses AI embeddings to index your vaults and integrate search over your thoughts into your workflow.
Auto Keyword Linker
9 months ago by Daniel Rhodes
Stop manually typing [[brackets]] around recurring terms. Configure keywords with variations once, and automatically link them as you write or across your entire vault.
Connections
8 months ago by Eric Van Cleve
Agent Client
4 months ago by rait-09
Bring AI agents into Obsidian via Agent Client Protocol (ACP), such as Claude Code, Codex and Gemini CLI.
Local REST API with MCP
4 months ago by Adam Coddington
A secure REST API and Model Context Protocol (MCP) server for your vault.
Note Companion
4 months ago by nexus-jpf
Note Companion: AI assistant for Obsidian that goes beyond just a chat. (prev File Organizer 2000)
Personal Assistant
4 months ago by edonyzpc
A plugin that harnesses AI agents and streamlining techniques to help you automatically manage Obsidian.
Large Language Models
3 months ago by eharris128
The LLM plugin gives Obsidian users access to local and web-based, large language models via several chat interfaces: modal, widget, FAB window, and commands.
Claudian
2 months ago by Yishen Tu
An Obsidian plugin that embeds Claude Code/Codex as an AI collaborator in your vault
Sidet
2 months ago by Jiao Yingxing
An easy-to-use AI chat plugin for Obsidian with side browsing, focused conversations, and vault-aware knowledge capture.
AI image analyzer
2 months ago by swaggeroo
Analyze images with AI to get keywords of the image.
Karpathy LLM Wiki
2 months ago by Greener-Dalii
Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.
Local LLM Hub
2 months ago by TAKESHI MORITA
All-in-one local AI hub for Obsidian — LLM chat with vault tools, MCP servers, RAG, workflow automation, encryption, and edit history. Fully private, no cloud required.
Gemini Helper
2 months ago by TAKESHI MORITA
AI chat, workflow automation, semantic search (RAG), LLM Wiki (OKF) powered by Google Gemini. Works on both desktop and mobile.
MCP Connector
2 months ago by istefox
Your Obsidian vault, exposed to Claude and any MCP client. Runs inside Obsidian, on-device semantic search, no cloud round-trip, no binary to download.
Discourse Graph
2 months ago by discoursegraphs
Workbuddian
2 months ago by jiang198012
Obsidian 插件:把本地 CodeBuddy CLI 或 Hermes agent 变成 vault 内 AI 聊天——流式回复、@引用、双后端切换。Obsidian plugin turning local CodeBuddy CLI or Hermes agent into an in-vault AI chat with streaming, @-references, and dual backends.
DeepSeek Harness Native
a month ago by wuruihi
Obsidian 侧边栏内驱动本地 DeepSeek Harness (DSH) Web GUI,支持 vault 双向桥接与 DSH 服务自动管理。
WorkBuddy
a month ago by Jason
obsidian plugin for workbuddy
ICOR for Life - Connect
a month ago by Paperless Movement S.L.
Your app.myicor.com account inside your vault: ICOR Journey and Growth Assignment dashboards, knowledge-base search, reflections synced as notes you own, and myICOR context for Claude sessions. Part of the ICOR for Life suite.
ICOR for Life - Chat
a month ago by Paperless Movement S.L.
Talk to your AI team where the knowledge lives. A Claude chat inside the vault: it sees the note you have open and the text you selected, answers in readable ICOR cards, and archives your sessions as notes. Part of the ICOR for Life suite.
Qiaomu Reader
17 days ago by 向阳乔木
已上架 Obsidian 社区插件市场:搜索 Qiaomu Reader 安装。Read EPUB, PDF and MOBI, highlight passages, keep linked notes and ask optional AI.