Compare · Salana vs Obsidian
Obsidian is a vault for you. Salana is a memory for your agents too.
Obsidian is a beautiful, private Markdown vault on your own disk. Salana keeps the same spirit, plain files you own, and adds what agents need: a shared memory every AI reads and writes, versions per run, and work that runs by itself.



SalanaOne memory you own, for you, your team and every AI agent, with every version kept.Which one fits you.
No winner for everyone. It depends on what you need.
- You want a fast, private Markdown vault on your own disk, mostly for yourself, and you enjoy assembling plugins.
- You do not need agents reading and writing it from anywhere, scheduled jobs or per-run history.
Salana fits when- You want AI agents to read and write your notes, from Claude, Codex, Gemini, Grok or any MCP client.
- Your team shares the memory, with access per person and per agent.
- You want automations that work from your notes, and every agent run kept and undoable.
The difference, in one picture.
Lives inside Obsidian, for Obsidian.




Yours, as plain files. Every AI you use reads it.
Side by side.
What we say about Obsidian links to Dynalist Inc.'s own pages, checked 16 October 2026. Tell us if something has changed.
SalanaUse them together.
Salana Sync puts your memory in Finder as a plain folder of Markdown and files. Open that folder as an Obsidian vault and write as you always have; your agents see every change.
memory.salana.ai/mcpOpen ~/Salana/<Organisation>/<Memory> as a vault. Notes stay plain Markdown, and every save is a version in Salana.
Questions.
Can I keep writing in Obsidian?
Yes. With Salana Sync your memory is a normal folder in Finder, and Obsidian can open it as a vault.
Are my notes still plain Markdown?
Yes. Salana stores notes and files byte for byte, and you can export everything as a plain folder any time.
What does Salana add?
Agents that read and write the memory from any AI, sharing per person and per agent, automations, and every version kept per run.
More comparisons.
Keep what you teach your AI. Whatever AI you use.
Start with one memory. Bring the tools you already have.
