Five AI plugins for Obsidian that help retain knowledge from notes

Andrey Menshikov, a senior developer at IBS, published on July 9, 2026, a review on Habr of five AI plugins for the Obsidian note-taking application, which, according to his experience, help prevent losing knowledge from personal notes, articles, and meetings.

Why Knowledge is Lost Without a System

Information is forgotten within a week if you don't return to it—formally, the note exists, but finding it among messages and files is difficult. The author has been using Obsidian as a working system for notes, ideas, preparing talks, and project documentation for over a year and describes five specific AI plugins that have formed an entire ecosystem around Obsidian.

"Formally, knowledge exists, but where is it?

In notes? In correspondence with someone?" — Andrey Menshikov, senior developer at IBS, in an article on Habr.

Which Plugins the Author Reviews

• Copilot (github.com/logancyang/obsidian-copilot) — a universal assistant with RAG support, works with OpenAI, Anthropic Claude, Google Gemini, OpenRouter, and Ollama; used for searching information, creating article outlines, summarizing, and meeting notes
• Smart Connections (github.com/brianpetro/obsidian-smart-connections) — semantic search by meaning, not keywords: builds embeddings of notes and finds thematically related entries, includes Smart Chat with an emphasis on local data processing
• Text Generator (github.com/nhaouari/obsidian-textgenerator-plugin) — text generation, rewriting, summarization, and expansion right in the editor, supports over 100 providers and models, and custom prompt templates
• Chat GPT MD (github.com/bramses/chatgpt-md) — saves dialogues with the model as markdown files directly in the knowledge base, useful for brainstorming and formatting research
• Local GPT (github.com/pfrankov/obsidian-local-gpt) — works through Ollama completely locally, data never leaves the device, eliminating concerns about NDA and confidentiality for work documentation

How These Plugins Are Used in Practice

The author lists six use cases: semantic search instead of keyword search, discovering hidden connections between notes, quickly processing an incoming information stream, creating flashcards for memorization, regularly reviewing the knowledge base, and dialoguing with your own knowledge base through RAG chat.

According to the author's conclusion, the quality of all these tools depends not on the volume of the knowledge base but on how atomic and clearly titled the notes are—one giant file is processed worse by plugins than a set of small connected entries.

What This Means

The ecosystem of AI plugins around Obsidian has grown so much that a personal knowledge base stops being just an archive of files and becomes a system you can have a dialogue with and that finds semantic connections on its own—provided the user writes notes atomically, not in one large document.

Frequently Asked Questions

Which of These AI Plugins for Obsidian Are Free?

All five—Copilot, Smart Connections, Text Generator, Chat GPT MD, and Local GPT—are distributed as open-source projects on GitHub.

Which

Plugin Should I Choose If Data Cannot Be Sent to External Services?

Local GPT: it works through Ollama completely on the user's device without sending data to external APIs, which is suitable for documents under NDA.

How

Does Smart Connections Differ from Regular Obsidian Search?

Smart Connections builds note embeddings and searches by meaning, not exact keyword matches, which allows it to find thematically related notes that regular search would miss.