It's more about "meta" data over the data itself. What seemed for me good enough (notes had hierarchy only around some topics of interest) ended up in being almost useless for AI agents. When I've seen for the first time how my notes were really structured (only two clouds and endless non-linked grid of random ideas and observations) I'd got an idea why it was useless for AI. Then I tried to remove some garbage myself, tried to do this with the help of agent, but ended up making a KB from scratch and cherry-pick notes from my old knowledge base. Now it looks like 4 separated clouds and only few random disconnected notes out there.
Last week I changed my job and this KB got quickly saturated with some information about company, contracts, people in company etc. This helped me to start off quickly on the new site, but the downside was that I concerned about what sorts of info had been stored in this KB. This Skill has helped me (along with basically `grep`) to ensure that there is no leakage and work is fully separated from anything else.
I put "wife's insights" into quotation marks, because, honestly, most of things contributed by my wife into this KB were really obvious or boring things which don't empower this KB in any way. She knows what it means ;)
Mostly to understand the structure of your knowledge base. To search across the KB it is more convenient to use Obsidian/gbrain itself.
Suppose you've been collecting thousands of notes from meetings, feedback from colleagues or code-reviews, "insights" and tips from you wife over the years. Aren't you curious what this KB contains and how it has evolved over time?
So, shortly it is a debug tool for your second brain.
Behavior model (B=MAP) by B. J. Fogg may give you more ideas on how to improve the idea of downvoting drivers and persuade rude drivers to reduce negative behaviour.
In my opinion, as a driver, I will be more than depressed once received downvotes from random drivers around me. Rude driving from my observations is tightly related to emotional factors. Adding punishment in a form of down-voting will just add more tension. Would be better to have more motivation to drive carefully and more ability to achieve that. Basically, informative road signs and fake highway patrols give more ability, immediate response and motivation.
Techs: Fullstack, mostly Python (2.5+, 3+), Django, Flask, FastAPI, Pydantic, Pandas, Jupyter Notebooks, ReactJS, Docker, Linux. Experimenting with Rust for high-performance/big-data tasks. Used to be a tech lead, SCRUM master, early stage/small companies preferred. Interests in MVP, legacy code, startups. I play tennis, chess and poker.
If donations make a sensitive income flow, why switch to paid SaaS offering ever?
Keep your OpenSource as a non-profit and develop SaaS as another brand, separately.
Offer a premium proprietary product as a separate product under the same brand.
This tool supports large files, works completely browser-side and doesn't require any uploads. Respects your privacy and shows fancy hex preview of the input.
I made this tool during weekend. "Base64" and all those base-* family encodings produce lots of questions and search requests in the web. On the other side, the encoding algorithm is very straightforward. Wondered if someone find useful my online base64 encode tool.