tarr1124

Honestly, "note app" is a stretch. What I wanted was a knowledge system modeled on PoIC, a Japanese index-card method that predated Evernote. I tried building it on Obsidian and other markdown tools for years and structured notes never stuck for me. I just wanted to talk into my phone and dump quick fragments, then have something extract knowledge and tasks out of them. LLMs and Claude Code closed most of the gap. Now journals, web clips, and daily deep-think sessions all land in it, and Claude Code semi-solves the tasks it pulls out. I'm probably ADHD and it seems to hit for that crowd. Most people would look at it and say "why not Obsidian" lol.

OSS, with the skill + CLI layer built around Claude Code: https://github.com/rillmd/rill

Mac app at https://rill.md/. Still very much in development. If you give it a spin, I'd love feedback either as a GitHub issue or right here.

Yeah, fair. The third-person thing is an old habit from parsing parents before I reply, but you're right that in a direct reply it reads cold. Second person from here on.

Selling would be nice, but a lot of solo builders are mainly in it for the building. The note app I wanted didn't exist anywhere. I was close to hiring a contractor to build it, so it's already worth tens of thousands of dollars to me. I want to make a bit off it but not run a real business. No VC, no employees. If it earns enough to pay my own salary, I get to keep building it as my job, which beats most startup exit math. Reaching maybe 100 people with the same problem is the target.

Three notetaking app attempts sitting in my private repos, all stalled at the gap between idea and free time. With Claude Code I finally got the one I really wanted out in two months. Building it has been the best hobby I've found. Beats games or scrolling. When you've been carrying an idea for years, the app that finally ships has more of you in it, and I'd bet we'll see a lot more of these from solo builders.

I wrote it. English is my second language, so I reach for "what X is pointing at" constructions a lot — partly as a self-check that I've parsed the parent correctly. If any specific claim in there looks wrong or generated, happy to have it pointed out.

Git is great as the durable layer, but what fiatpandas is pointing at is a bit different — real-time awareness that the agent is active right now, not a retrospective diff.

I've been working on this split in a side project (https://github.com/rillmd/rill — vault layer on top of Claude Code). Git still handles the durable side for free, since the CLI agent just writes files and commits normally. The live side comes from Claude Code hooks (UserPromptSubmit / Stop / PostToolUse) appending to a plain activity-log.md that the Electron GUI tails. Cruder than Google Docs cursor presence, but cheap — and the log itself is just another markdown file in the vault, same data model as everything else.

One trade-off: going the other direction and letting the frontend detect edits via FSEvents-style watching runs straight into the reconciliation issues the Zettlr subthread is about. Hooks on the agent side are less elegant but sidestep the whole class.

Obsidian and these newer tools share markdown + local files, but they're aimed at different assumptions about who reads and edits the vault. Obsidian's default is "human reads and curates; plugins optionally enhance." The AI-first cohort (Tolaria, Sig in the sibling comment, and several others) assumes the AI reads and writes as a first-class agent, which makes design choices like how the app reacts to files changing underneath it (cf. the Zettlr comment downthread) a core concern rather than an edge case.

Worth watching how each of these tools positions the AI: as a UX copilot inside the editor, or as an autonomous agent with file-system access via local CLI/MCP.