In their own words

1. I use it to keep my different notes and writing projects organized and so my ChatGPT remembers everything we worked on so I don't have to start over from the beginning every time I leave my project and come back later. It hasn't replaced anything. I was lucky enough to find it right from the beginning

   September 2026

2. We use Hjarni to store scenario preparations, character sheets, and house rules for our "Cosmere - Stormlight Archive" tabletop RPG campaign. And it's Great ;)

   September 2026

3. I use Hjarni as the shared archive behind a long-running creative project with ChatGPT. Instead of depending on summaries or trying to remember which chat something lived in, I can keep the original material in one place and let ChatGPT search, retrieve, and update it across conversations.

   September 2026

4. Hjarni has basically given ChatGPT a notebook for me. I use it to keep useful context across conversations—especially things like Air Cadets, ongoing projects, preparation, and everyday plans—so I don't have to keep explaining the same things over and over. It’s replaced a lot of manually keeping track of context, and having that information available makes ChatGPT feel much more consistent and actually useful over time.

   September 2026

5. I work on a lot of coding projects with claude and codex and I find Hjarni very useful to organize information and limit context needed for projects. I love Hjarni because context retrieval is one of the most expensive things agents have to do. I have been using hjarni to basically package relevant context for ai projects so agents get what they need without racking up token costs

   September 2026

6. I mainly use Hjarni as a shared external notebook between me and different AI agents. I can discuss game design with ChatGPT while I'm away from my computer, have our decisions written into Hjarni, and later another agent working directly on the project can read those notes and use them as context. It also works in the other direction. This greatly reduces the amount of context I have to manually copy between chats and agents.

   September 2026

7. I use Hjarni to keep track of the characters, events and background details in a story I'm writing. I've given both ChatGPT and Claude access to it so they can check and update the same notes. I'd tried several ways of handling this before. Too much time went on uploading files and explaining things we'd already worked out. Hjarni has cut down on that and made it easier to carry on when I start a new chat or switch between assistants. I tested it before upgrading, then signed up straight away. I'd recommend it to anyone using AI for an ongoing writing project, especially if they use more than one assistant.

   September 2026

8. Between Claude and ChatGPT, it keeps the respective AI platforms as the intelligence and reasoning layer while context and memory are transferred and centrally updated. It reduces restart and stand-up time when handing off an ongoing chat or project to a new conversation.

   August 2026

9. I'm using Hjarni to host something like .ini files for my Claude projects. I write a lot, and Hjarni holds a style guide of how to write like me, which Claude can fine-tune when it arrives at new insights about my style.

   August 2026

10. I use Hjarni for my thesis. Having my assistant search and edit my notes directly has completely replaced the tedious back-and-forth of pasting context into external chat windows.

    August 2026

11. I run a one person business and work with Claude daily. Hjarni is the layer where Claude and I keep shared working documents, mainly Claude's work notes and an idea inventory that we both read and write.

    Before Hjarni, my detailed notes lived in Obsidian. The MCP setups all assume your main computer is running and Claude is talking to it locally. I needed Claude to write from my iPad with no dependency on my Mac being awake. I went through a device bridge, a headless sync client on a VPS, git syncing the vault, and putting the vault on a server. Hjarni is hosted with MCP always connected, so that all went away. Obsidian is still my permanent human curated archive. Hjarni took over the part Obsidian was never shaped for.

    I also compared a note app I used for structured documents. Its API is block level, so updating a 19 item checklist meant 19 separate calls. In Hjarni, Claude replaces a section, appends to a section, checks an item. The drop in call count was immediate and obvious. That is the single biggest difference. Hjarni is shaped the way an assistant actually edits a document.

    The design decisions around data ownership, full export, and keeping the feature scope honest were a real part of why I chose it.

    August 2026

12. This replaces Obsidian. I didn't like how it worked, it was slow and rather clunky. Hjarni is exactly what I needed: my notes, generated by AI, and being able to share them with my team, so our AI agents always have the full context of everything.

    July 2026

13. I wanted a cloud knowledge base I could use as memory for my AI, in plain Markdown, with read and write access. Nothing else fit. Hjarni did. What sold me was how light and well defined the MCP is. My AI used to choke when I pasted Markdown and config files into a chat. It reads them perfectly from Hjarni. The folder-level AI instructions and the knowledge graph are the parts I did not know I needed.

    June 2026

14. Hjarni ran the whole Labeur launch. Scope decisions, landing page copy, App Store submission, launch day checklist, all in one place and all in sync with Claude. I stopped re-explaining myself to the AI. From first sketch to live in the store.

    April 2026

This wall grows slowly on purpose. Reviews come in through the app and by email, and only go up when the reviewer has okayed the quote and chosen how to be credited.