--- title: "Choose Obsidian or Logseq by how an AI reads the files" description: "Compare Obsidian and Logseq for AI memory by file format, block metadata, AI access routes, and portability, then test both with your own notes." canonical: "https://scalewithsearch.com/articles/obsidian-vs-logseq-for-ai" date: "2026-01-28" modified: "2026-09-25" --- ## Site navigation - [Scale With Search](https://scalewithsearch.com/) - Real estate - Real estate - [Real estate](https://scalewithsearch.com/for/real-estate) - Work - Start here - [Send your brief](https://scalewithsearch.com/work#send-your-brief) - [Prepare your six-question brief](https://scalewithsearch.com/work#prepare-your-six-question-brief) - Build - [Site build, content library with SEO, signal desk](https://scalewithsearch.com/work) - For your business - Trades and home services - [Auto body and collision shops](https://scalewithsearch.com/for/auto-body-and-collision-shops) - [Foundation and home repair contractors](https://scalewithsearch.com/for/foundation-and-home-repair) - [Garage door and fencing contractors](https://scalewithsearch.com/for/garage-door-and-fencing-contractors) - [HVAC contractors](https://scalewithsearch.com/for/hvac-contractors) - [Janitorial and commercial cleaning companies](https://scalewithsearch.com/for/janitorial-and-commercial-cleaning) - [Locksmiths](https://scalewithsearch.com/for/locksmiths) - [Moving companies](https://scalewithsearch.com/for/moving-companies) - [Pest control companies](https://scalewithsearch.com/for/pest-control-companies) - [Plumbing and electrical contractors](https://scalewithsearch.com/for/plumbing-and-electrical-contractors) - [Restoration and water or fire damage companies](https://scalewithsearch.com/for/restoration-and-water-fire-damage) - [Roofing companies](https://scalewithsearch.com/for/roofing-companies) - [Towing companies](https://scalewithsearch.com/for/towing-companies) - [Tree services and landscaping companies](https://scalewithsearch.com/for/tree-services-and-landscaping) - [Solar installers](https://scalewithsearch.com/for/solar-installation) - [General contractors](https://scalewithsearch.com/for/general-contractors-and-construction) - [Paving, concrete, and flooring contractors](https://scalewithsearch.com/for/paving) - Practices and professional services - [Bookkeeping and tax practices](https://scalewithsearch.com/for/bookkeeping-and-tax-practices) - [Dental practices](https://scalewithsearch.com/for/dental-practices) - [Family and criminal defense law firms](https://scalewithsearch.com/for/family-and-criminal-defense-law-firms) - [Med spas and aesthetics practices](https://scalewithsearch.com/for/med-spas-and-aesthetics) - [Personal injury law firms](https://scalewithsearch.com/for/personal-injury-law-firms) - [Veterinary clinics](https://scalewithsearch.com/for/veterinary-clinics) - [Gyms and fitness studios](https://scalewithsearch.com/for/fitness) - [Therapy and outpatient health practices](https://scalewithsearch.com/for/therapy-and-outpatient-health) - [Medical billing companies](https://scalewithsearch.com/for/medical-billing) - [Insurance agencies](https://scalewithsearch.com/for/insurance-agencies) - [Financial advisors](https://scalewithsearch.com/for/financial-advisors) - [Property management companies](https://scalewithsearch.com/for/property-management) - [Recruiting and staffing agencies](https://scalewithsearch.com/for/recruiting-and-staffing) - [Architects and interior designers](https://scalewithsearch.com/for/architects-and-interior-designers) - [Logistics and supply chain companies](https://scalewithsearch.com/for/logistics-and-supply-chain) - Agencies, MSPs, and manufacturing - [IT and managed service providers](https://scalewithsearch.com/for/it-and-managed-service-providers) - [Machine shops and precision manufacturers](https://scalewithsearch.com/for/machine-shops-and-precision-manufacturing) - [Marketing agencies and freelancers](https://scalewithsearch.com/for/marketing-agencies-and-freelancers) - [SEO agencies and consultants](https://scalewithsearch.com/for/seo-agencies-and-consultants) - [Small manufacturers and fabricators](https://scalewithsearch.com/for/small-manufacturers-and-fabricators) - Restaurants, shops, studios, and nonprofits - [Restaurants and hospitality businesses](https://scalewithsearch.com/for/restaurants-and-hospitality) - [Retail stores and ecommerce sellers](https://scalewithsearch.com/for/retail-and-ecommerce) - [Photographers, event planners, and travel agents](https://scalewithsearch.com/for/photographers) - [Churches and nonprofits](https://scalewithsearch.com/for/churches-and-nonprofits) - [All industries](https://scalewithsearch.com/for/) - Learn - For your office - [Office job guides](https://scalewithsearch.com/guides/) - [Browser calculators](https://scalewithsearch.com/tools/) - Start here - [How it works](https://scalewithsearch.com/how-it-works) - [Free Starter Kit](https://scalewithsearch.com/kit/business-memory-starter-kit.zip) - [Synthetic specimen](https://scalewithsearch.com/specimen/working-session-specimen.zip) - Guides - [The Complete Guide to Business Memory for AI Agents](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [The Complete Small-Business Guide to AI Agent Governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [The Complete Guide to Leaving Vendor AI Memory](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - Articles by cluster - [Business memory](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [Agent governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [Migration and ownership](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - For machines - [llms.txt](https://scalewithsearch.com/llms.txt) - [llms-full.txt](https://scalewithsearch.com/llms-full.txt) - [Machine view](https://scalewithsearch.com/?view=machine) - Company - Evidence - [Proof](https://scalewithsearch.com/proof) - Company - [About](https://scalewithsearch.com/about) # Choose Obsidian or Logseq by how an AI reads the files. Obsidian and Logseq share a core idea: local, plain-text notes that you own. Both use Markdown, with differences. Both have graph views. Both let an AI tool read your notes. They differ in how they structure a file. Obsidian treats a note as a document. Logseq treats a note as an outline of blocks. For AI memory, that difference changes what the model sees when it opens the file. This article compares the two as they stood in January 2026, when it was first written. It shows what a model sees in each format. It ends with a test that you can run with your own notes. ## Know how Logseq structures notes Logseq is an outliner. Every bullet is a block, and every block is an addressable unit. You can reference one block from another page. The daily journal makes it fast to capture notes in date order. The file format is close to Markdown, but it is not pure Markdown. Logseq adds metadata for block references, properties, and hierarchy. Open a Logseq file in a plain text editor, and you see extra syntax that keeps the block structure intact. Logseq also develops a version that stores graphs in a database, not in Markdown files. Check which graph type you use. If your graph lives in a database, a file-reading agent cannot read it as Markdown. ### Logseq AI routes in January 2026 A community MCP server, listed on Glama as `logseq-ai`, let external AI tools such as Claude Desktop and Windsurf work with a Logseq graph. It exposed page, block, journal, and task operations as tools through Logseq's local HTTP API. [Glama: logseq-ai MCP server](https://glama.ai/mcp/servers/@HarrisonTotty/logseq-ai) The plugin set at that date included: - the Logseq AI MCP server, for reads and edits by external assistants through the local HTTP API; - Lain, an AI assistant inside Logseq; - AI Assistant, for text generation and rewrites with custom prompts; - the GPT-3 plugin, for note help through the ChatGPT API; - AssistSeq, which indexes related notes for context-aware conversations. The MCP route gives an AI structured access to the graph. The model still has to interpret block references and Logseq metadata when it reads raw files. ## Know how Obsidian structures notes Obsidian stores notes as standard Markdown files: headings, lists, links, and text. Obsidian supports block references too, but it writes a block ID into the file only when you create a reference to that block. The open-source `kepano/obsidian-skills` repository gives agents such as Claude Code skills for Obsidian Markdown, Bases, and JSON Canvas files. The files were already in a format that models read well, so that route needed less translation than a block graph. Obsidian's AI plugin set at that date included: - Smart Connections, for semantic search, with a free version and a paid tier; - Copilot, a chat interface with cloud and local model support; - AI Assistant, with access to Claude, GPT, DALL·E, and Whisper; - Text Generator, with support for OpenAI, Anthropic, Google, and local models. When Claude Code reads an Obsidian vault, it sees Markdown with a clear heading structure and little metadata. For the wider case for plain files, read [why plain text is the durable layer for AI memory](/articles/plain-text-ai-memory). ## See what the model reads A model reads text in order. It does not resolve block references the way Logseq's interface does. A Logseq file, opened as text: ``` - Block with some content id:: 65a3c8e1-8f24-4a3d-9e12-3f5d6c7b8a90 - Nested block ((65a3c8e1-8f24-4a3d-9e12-3f5d6c7b8a91)) id:: 65a3c8e1-8f24-4a3d-9e12-3f5d6c7b8a92 ``` An Obsidian file, opened as text: ``` ## Heading - List item with content - Nested item - Another item [[Link to another note]] ``` The second format carries less metadata and a clearer hierarchy. The first format has a larger problem than noise. The reference `((65a3c8e1-...))` points to content in another block. A model that reads only this file sees an ID, not the referenced text. Unless a tool resolves the reference, that content is missing from the context. ## Weigh structured access against readable files Both tools give AI access to local notes. They differ in what the AI can extract. The Logseq MCP route gives structured access. The AI can query a block, read its properties, and follow a reference through the tool. That matters when your work depends on block-level detail. Obsidian files give readable access. The AI reads a whole document, and headings and lists give the hierarchy directly. No translation layer sits between the file and the model. For persistent AI memory, readable files carry a practical advantage. Any tool that reads text can use them, including a tool that does not exist yet. For more on that advantage, read [how to replace the model and keep business memory](/articles/replace-the-model-keep-business-memory). ## Compare the two | Factor | Logseq | Obsidian | |---|---|---| | File format | Markdown with block metadata, or a database graph | Standard Markdown | | Structure | Outliner, block-based | Document, heading-based | | AI integration in January 2026 | Community MCP server, plugins | Agent skills repository, plugins, direct file reads | | Readability for a model | Block IDs and references need resolution | Headings and lists read as written | | Storage | Local files or local database | Local files | | Cost | Free | Free, with optional paid Sync | | Best fit | Block-level work and outliner capture | AI memory and portability | ## Test both with your own notes The table describes typical files. Your notes decide the result. Run this test with one real page. 1. Pick a page that you use for work, such as a client note or a project plan. 2. Keep the Logseq version as it is. 3. Write the same content in Obsidian as a document with headings. 4. Start a fresh AI session for each version. Give it only that file. 5. Ask three questions: one fact, one relationship between items, and one next action. 6. Record which version answered each question from the file alone. A failure on the relationship question often points to an unresolved block reference. Check whether the answer needed text that lived in another block. Here is an example. A project plan page has a "Next steps" block. One step reads "Order materials after ((ID))", and the reference points to a "Deposit received" block on the client page. You ask, "What must happen before you order materials?" The Obsidian version states "after the deposit is received" in the text, so the model answers from the file. The Logseq version shows only the ID. The model either says that it cannot tell, or it guesses. Record the guess as a failure, because it did not come from the file. If you stay with Logseq, you can export a cleaner copy for an agent. This command removes block ID lines from a page: ``` sed '/^[[:space:]]*id:: /d' page.md > page-clean.md ``` It does not resolve `((...))` references. Replace each reference with its text before you give the page to an agent, or let an MCP tool resolve it. ### Find the text behind a reference Resolve the references before you remove the `id::` lines, because the search needs them. A file-based graph keeps its pages in `pages/` and `journals/` folders. The target block carries the same ID on an `id::` line directly under its text. Search the graph for the ID: ``` grep -rn -B1 "id:: 65a3c8e1-8f24-4a3d-9e12-3f5d6c7b8a90" pages/ journals/ ``` The `-B1` flag prints one line above the match, which is the block text. If the block has more than one line, or other property lines above the ID, increase the number until the output shows the full block. Paste that text in place of the reference in your copy. Then run the `sed` command on the copy. For a method to decide what a task should read, see [what context an agent should read](/articles/what-context-should-an-agent-read). ## Choose by how you work Choose Logseq if you prefer outliner capture and your work needs block-level references. The MCP route gives an AI working access to the graph. Choose Obsidian if your first goal is a knowledge base that any AI tool can read. Headings and lists give you hierarchy without block metadata, and you give up little outliner function for most business notes. The [Obsidian business memory guide](/articles/obsidian-ai-memory-for-business) shows how to structure the vault for agent use. ## Related: AI memory - [Choose Obsidian or Roam Research by where an AI can reach your notes](/articles/obsidian-vs-roam-for-ai) - [Use an Obsidian vault as the knowledge base Claude Code reads](/articles/what-is-obsidian-for-ai) - [Apple Notes vs Obsidian for AI Memory: Fast Capture or Agent-Readable Record?](/articles/apple-notes-vs-obsidian-ai-memory) ---- ```text .|########||. .|########||. .|########||. |##||. .||##|. |##||. .||##|. |##||. .||##|. |#|. .|#|. |#|. .|#|. |#|. .|#|. |#| |#| |#| |#| |#| |#| .#| |#. .#| |#. .#| |#. .#. .#| .#. .#| .#. .#| |#. .#| |#. .#| |#. .#| |# ...... #| |# ...... #| |# ...... #| .# ||#########| #| .# ||#########| #| .# ||#########| #| .#. |######||######|. .#. .#. |######||######|. .#. .#. |######||######|. .#. #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# # .||####|###########################|. # # .||####|###########################|. # # .||####|###########################|. # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || #. .######|#|#########| .# #. .######|#|#########| .# #. .######|#|#########| .# .#. |#####||||#####| .#. .#. |#####||||#####| .#. .#. |#####||||#####| .#. |# ||########|| #. |# ||########|| #. |# ||########|| #. |# ...... #| |# ...... #| |# ...... #| |#. .#| |#. .#| |#. .#| |#. .#. |#. .#. |#. .#. .#| |#. .#| |#. .#| |#. |#| |#| |#| |#| |#| |#| .|#|. .|#|. .|#|. .|#|. .|#|. .|#|. |##||. .||##| |##||. .||##| |##||. .||##| .||########||. .||########||. .||########||. Scale With Search 2026 [scalewithsearch.com](https://scalewithsearch.com) ```