Key Takeaways
- Smart Connections (Obsidian): finds semantically related notes as you write, plus a chat pane that references your vault.
- Copilot for Obsidian (Obsidian): chat pane with multiple provider support and a Vault QA mode that retrieves answers from across your whole vault.
- Text Generator (Obsidian): generates and inserts AI text directly into a note using customizable templates.
- logseq-copilot (browser extension, not Obsidian): adds an AI chat side panel to Logseq and can summarize a web page you are browsing directly into your notes.
- BMO Chatbot (Obsidian): a lightweight chat sidebar for talking with a local or cloud model while referencing the note you have open.
- All five support connecting to a local model runner such as Ollama or LM Studio, in addition to cloud API providers.
📍 In One Sentence
Smart Connections surfaces semantically related notes and adds a vault chat pane, Copilot for Obsidian adds multi-provider chat with a Vault QA retrieval mode, Text Generator inserts AI text into notes from templates, logseq-copilot is a Chrome/Firefox browser extension (not an Obsidian plugin) that adds an AI chat panel and web-page summarization to Logseq, and BMO Chatbot is a lightweight chat sidebar scoped to the note you have open — all five support local models via Ollama or LM Studio alongside cloud providers.
💬 In Plain Terms
These are five separate community tools that add AI features to two different note-taking apps. Three of them (Smart Connections, Copilot for Obsidian, Text Generator, and also BMO Chatbot) install inside Obsidian. One (logseq-copilot) is a browser extension you install in Chrome or Firefox that then talks to Logseq — it is not something you install from inside Obsidian or Logseq itself. Each tool does one job well rather than everything at once: finding related notes, chatting across your whole vault, generating text from a template, summarizing a webpage into your notes, or chatting about a single open note.
📌Note: This article describes documented plugin capabilities from each project's own public repository. It is not an independent benchmark of response speed or output quality, and it does not claim one plugin is technically superior to another — the comparison is about what each tool is built to do, not which produces the "best" answer.
What AI Plugins Exist for Obsidian and Logseq?
Obsidian and Logseq are both note-taking apps built around local markdown files, and both have community plugin ecosystems that add AI features on top of that local-first foundation. Obsidian plugins install from inside the app itself, through its community plugin browser or a beta-installer like BRAT. Logseq has its own plugin system too, but the tool covered in this guide — logseq-copilot — is not a Logseq plugin at all; it is a browser extension you install separately in Chrome or Firefox that then connects to a running Logseq instance.
- Obsidian plugins in this guide: Smart Connections, Copilot for Obsidian, Text Generator, and BMO Chatbot — all installed from within Obsidian.
- Logseq tooling in this guide: logseq-copilot, installed as a Chrome or Firefox browser extension, not through Logseq's own plugin system.
- None of these five tools is made by Obsidian's or Logseq's core team — all are independent, community-maintained projects.
- All five are free, open-source projects you can inspect on their public GitHub repositories before installing.
Which One Should You Install First?
Match the plugin to the specific problem you want solved, not to a general idea of "AI notes." Each of the five tools below is built around one core job.
- Use Smart Connections if your problem is "I have thousands of notes and can't find the ones related to what I'm writing right now."
- Use Copilot for Obsidian if your problem is "I want to ask a question and get an answer pulled from across my whole vault, with flexibility over which AI provider answers it."
- Use Text Generator if your problem is "I do the same kind of writing task repeatedly (meeting notes, outlines, summaries) and want a reusable AI template for it."
- Use logseq-copilot if you use Logseq (not Obsidian) and want an AI chat panel plus the ability to summarize a webpage you are reading straight into your graph.
- Use BMO Chatbot if you want the smallest possible footprint — a simple chat sidebar about the one note you have open, without a vault-wide index.
What Is Smart Connections For — And What Is It Not For?
Smart Connections is an Obsidian plugin that finds notes semantically related to what you are writing or reading, going beyond Obsidian's built-in exact-text backlinks. It builds embeddings of your notes and shows a "related notes" view alongside your editor, plus a separate chat pane you can use to ask questions with your vault as context. It supports both a bundled local embedding model that runs with no external setup, and connections to external API providers for embeddings and chat if you prefer those instead.
Use Smart Connections if
- You want to discover notes conceptually related to the note you have open, not just ones linked by an exact `[[wikilink]]`
- You want this working immediately, without configuring an API key or running a separate local server first
- You want a lightweight chat pane that references your vault, in addition to the related-notes view
- You want the option to swap between a bundled local embedding model and an external provider later
Do not rely on Smart Connections if
- You need a deep retrieval-QA mode that synthesizes an answer from many notes at once — that is closer to Copilot for Obsidian's Vault QA mode
- You need template-driven text generation with reusable prompt variables — that is Text Generator's job
- You are working in Logseq rather than Obsidian — Smart Connections is an Obsidian plugin only
What Is Copilot for Obsidian For — And What Is It Not For?
Copilot for Obsidian is a chat plugin that adds a conversational sidebar supporting multiple AI providers, plus a Vault QA mode that retrieves relevant passages from across your entire vault to answer a question. It supports connecting to providers including OpenAI, Anthropic, Google, and Azure, as well as local models through Ollama or LM Studio, so you are not locked into a single vendor. Beyond open-ended chat, it also supports custom prompt templates and commands you can trigger on selected text or the active note.
Use Copilot for Obsidian if
- You want a single chat interface that can switch between several cloud providers and local models without reinstalling anything
- You want to ask a question and have the plugin retrieve and cite relevant passages from across your entire vault, not just the open note
- You want reusable custom prompt commands you can run against selected text or the open note
- You are comfortable with a plugin that has more configuration surface than a minimal chat sidebar, in exchange for that flexibility
Do not rely on Copilot for Obsidian if
- You want the absolute simplest, lowest-configuration chat plugin — BMO Chatbot has a smaller feature surface and less to set up
- You want a related-notes sidebar that appears passively as you write — that is Smart Connections' core feature, not Copilot's
- You need the AI features to work in Logseq rather than Obsidian
What Is Text Generator For — And What Is It Not For?
Text Generator is an Obsidian plugin built to generate AI text and insert it directly into a note, driven by customizable templates and prompts, rather than through an open-ended chat conversation. It supports OpenAI and local models through Ollama, LM Studio, and LocalAI. The core workflow is different from a chat plugin: you select a template (or write your own prompt), run it against the open note or selected text, and the output is written into the note itself.
Use Text Generator if
- You do the same writing task repeatedly — meeting-note expansion, outline generation, summarization — and want a reusable, one-click template for it
- You want the AI output to land directly in your note as text, not in a separate chat window you then have to copy from
- You want to write and share your own custom prompt templates with specific frontmatter variables
- You are fine running it against local models via Ollama, LM Studio, or LocalAI when you do not want to use a cloud provider
Do not rely on Text Generator if
- What you actually want is a back-and-forth conversation about your notes — that is a chat plugin's job, not a template-generation plugin's
- You want semantic search across your vault to find related notes — Text Generator does not build a vault-wide embedding index
- You are working in Logseq — Text Generator is an Obsidian-only plugin
What Is logseq-copilot For — And What Is It Not For?
logseq-copilot is a browser extension for Chrome and Firefox, not an Obsidian plugin and not a Logseq plugin installed through Logseq itself. It runs inside your browser and connects to a Logseq graph running locally, adding an AI chat side panel and the ability to summarize the web page you are reading directly into your Logseq notes. Because it is a browser extension, it is the odd one out in this comparison: it only makes sense if you use Logseq, and installing it will do nothing useful for an Obsidian vault.
Use logseq-copilot if
- You use Logseq (not Obsidian) as your notes app
- You want to capture and summarize web pages you are reading directly into your Logseq graph, without switching apps to write the summary yourself
- You want an AI chat panel available alongside your browsing, connected to your Logseq graph as context
- You are comfortable installing and managing it as a browser extension rather than through an in-app plugin manager
Do not install logseq-copilot if
- You use Obsidian — this tool does nothing for an Obsidian vault; use Smart Connections, Copilot for Obsidian, Text Generator, or BMO Chatbot instead
- You do not use a Chromium-based browser or Firefox — it will not run
- You want vault-wide semantic search inside your notes app itself, rather than a browser-side panel
What Is BMO Chatbot For — And What Is It Not For?
BMO Chatbot is a lightweight Obsidian plugin that adds a chat sidebar for talking with a local or cloud model, with the open note available as reference context. It supports local models via Ollama and LM Studio as well as several cloud providers, and it emphasizes a smaller, privacy-first setup over a large feature surface. It does not build a vault-wide embedding index and does not offer template-driven generation — its scope is deliberately narrower than Copilot for Obsidian or Smart Connections.
Use BMO Chatbot if
- You want the smallest, simplest possible chat plugin for Obsidian, with minimal setup
- Your main use case is chatting about or summarizing the single note you have open, not the whole vault
- You want a local-first default, using Ollama or LM Studio, without needing a cloud account
- You do not need Vault QA-style retrieval across thousands of notes
Do not rely on BMO Chatbot if
- You need answers synthesized from across your entire vault — that is Copilot for Obsidian's Vault QA mode, not BMO's scope
- You want a passive related-notes sidebar that surfaces connections as you type — that is Smart Connections' job
- You want template-driven text inserted into notes with reusable prompt variables — that is Text Generator's job
How Do These Five Tools Compare?
The table below lines up all five tools on app, install method, core job, and local-model support — use it to confirm your pick before installing.
Tool | Link | App | Install Method | Core Job | Local Model Support |
|---|---|---|---|---|---|
| Smart Connections | github.com/brianpetro/obsidian-smart-connections | Obsidian | Obsidian community plugin browser | Semantic related-notes discovery + vault chat pane | Bundled local embedding model; local/cloud chat providers configurable |
| Copilot for Obsidian | github.com/logancyang/obsidian-copilot | Obsidian | Obsidian community plugin browser | Multi-provider chat + Vault QA retrieval + custom prompt commands | Ollama, LM Studio, plus OpenAI, Anthropic, Google, Azure |
| Text Generator | github.com/nhaouari/obsidian-textgenerator-plugin | Obsidian | Obsidian community plugin browser | Template-driven text generation inserted into notes | Ollama, LM Studio, LocalAI, plus OpenAI |
| logseq-copilot | github.com/EINDEX/logseq-copilot | Logseq (via browser) | Chrome Web Store / Firefox Add-ons — not a Logseq plugin | AI chat side panel + summarize web pages into Logseq | Connects to a locally running Logseq graph; provider support per extension settings |
| BMO Chatbot | github.com/longy2k/obsidian-bmo-chatbot | Obsidian | Obsidian community plugin browser | Lightweight chat sidebar scoped to the open note | Ollama, LM Studio, plus several cloud providers |
This table reflects documented features from each project's own public repository, not independent hands-on benchmarking. No speed, accuracy, or output-quality claims are made — the comparison is limited to what each tool is documented to do.
Who Should Use Which Plugin?
The right combination depends on the size of your vault, how much you write versus search, and whether you use Obsidian or Logseq at all.
Large, long-running Obsidian vault (thousands of notes)
Start with Smart Connections for related-notes discovery, and add Copilot for Obsidian's Vault QA mode when you need a synthesized answer pulled from many notes at once rather than a list of related ones.
Repeatable writing workflows (meeting notes, weekly reviews, outlines)
Text Generator is built specifically for this — set up a template once and reuse it, instead of retyping the same prompt into a chat window every time.
Minimal setup, privacy-first, single-note focus
BMO Chatbot covers this without the configuration overhead of a vault-wide index — a good fit if you mainly want to chat about or summarize whatever note is open.
Logseq users who browse and research a lot
logseq-copilot is the only option on this list built for Logseq, and it is aimed specifically at capturing and summarizing what you are reading in the browser straight into your graph.
Common Mistakes When Choosing an AI Note-Taking Plugin
Most disappointment with these tools traces back to picking one for a job it was not built to do, rather than an actual defect in the plugin.
Mistake 1: Installing logseq-copilot expecting it to work in Obsidian
logseq-copilot is a browser extension built specifically for Logseq. It has no connection to Obsidian and installing it will not add anything to an Obsidian vault.
Mistake 2: Expecting Smart Connections to answer synthesized questions across many notes
Smart Connections is built around surfacing related notes, not synthesizing a single answer from many of them. If you want a retrieval-based answer pulled from across your vault, Copilot for Obsidian's Vault QA mode is the closer fit.
Mistake 3: Using a chat plugin for repeatable template work
Retyping the same prompt into a chat window every week for the same task (meeting-note expansion, weekly review) is exactly what Text Generator's reusable templates are built to replace.
Mistake 4: Assuming every plugin requires a cloud API key
Smart Connections ships with a bundled local embedding model that needs no external API key, and the other four all support connecting to a local model runner like Ollama or LM Studio if you prefer not to use a cloud provider.
What Are the Limitations of These Plugins?
Each tool has real limits worth naming directly rather than glossing over, whichever one you choose.
- None of these five tools is officially built or maintained by the Obsidian or Logseq core teams — they are independent, community-maintained open-source projects, and long-term maintenance depends on their individual maintainers.
- This article has not independently benchmarked response speed, retrieval accuracy, or output quality across the five tools, and does not claim one is technically superior to another.
- Cloud provider connections (OpenAI, Anthropic, Google, Azure, and others) require your own account and API key with that provider, billed to you directly — none of these plugins includes free bundled cloud usage.
- Local model use through Ollama or LM Studio requires installing and running that separate tool yourself; none of these five plugins bundles its own local inference engine beyond Smart Connections' embedding model.
- logseq-copilot depends on your browser and a running Logseq graph — it does not function as a standalone tool.
- No independently verified pricing, download-count, or version information is included in this article for any of the five projects — check each project's own public repository for up-to-date details.
Frequently Asked Questions
What is the best AI plugin for Obsidian?
There is no single best plugin — Smart Connections, Copilot for Obsidian, Text Generator, and BMO Chatbot each solve a different problem (related-notes discovery, vault-wide chat, template generation, and lightweight single-note chat, respectively). Most users combine two or three rather than picking just one.
Can I use local AI models with these Obsidian plugins?
Yes. Smart Connections, Copilot for Obsidian, Text Generator, and BMO Chatbot all support connecting to a local model runner such as Ollama or LM Studio, in addition to cloud providers.
What's the difference between Smart Connections and Copilot for Obsidian?
Smart Connections is built around discovering notes semantically related to what you are writing, plus a vault chat pane. Copilot for Obsidian is built around a multi-provider chat interface with a Vault QA mode that retrieves and synthesizes answers from across your entire vault. Many users run both together.
Does Text Generator work with local models?
Yes. Text Generator supports OpenAI as well as local models through Ollama, LM Studio, and LocalAI.
Is logseq-copilot an Obsidian plugin?
No. logseq-copilot is a Chrome and Firefox browser extension built for Logseq. It has no connection to Obsidian and does not work with an Obsidian vault.
What does BMO Chatbot do?
BMO Chatbot is a lightweight Obsidian chat sidebar for talking with a local or cloud model, using the open note as reference context. It is a smaller-footprint alternative to Copilot for Obsidian for users who mainly want single-note chat.
Can I use multiple AI plugins in Obsidian at once?
Yes. These plugins are not mutually exclusive — many users run Smart Connections alongside Copilot for Obsidian or Text Generator, since each covers a different job rather than competing to do the same one.
Do these plugins send my notes to the cloud?
Only if you configure them to use a cloud provider. Smart Connections ships with a bundled local embedding model requiring no external API key, and the other tools all support local models via Ollama or LM Studio as an alternative to cloud providers — but using a cloud provider does send the relevant note content to that provider for processing.
What is Vault QA mode in Copilot for Obsidian?
Vault QA is a retrieval mode in Copilot for Obsidian that searches across your entire vault for passages relevant to a question and uses them to generate an answer, rather than only referencing the single note you have open.
Which plugin should I install first?
If you use Obsidian and are unsure where to start, Smart Connections is a reasonable first install — it works with zero configuration using its own bundled local embedding model. If you use Logseq instead, logseq-copilot is the only tool in this comparison built for it.