Dragonish

I use obsidian, forgejo, renovate bot and some hugo websites as part of my knowledge garden. I am very happy with my setup, but i think “overkill” probably would describe what i have built. it has organically grown, and some less technical folks in my life follow a slimmed down version of this. I keep a note called _focus that i go to when i am overwhelmed. It contains my “seven W’s”, which are links to separate notes which are purposefully kept simple

Who am I?
What do I want?
Why do I want the things I want?
When am I going to do these?
What are the things I will consistently do to accomplish these?
With Whom I'm going to surround myself for leverage
Where will I do this; which tools will I use?

Whenever i am overwhelmed or feeling like my process is not working, this focus note helps keep me on track. It seems like you may benefit from a similar process.

Forgejo is great! it helps me keep track of different software i use and follow. It is where i store my obsidian vault (i only use 1). Git lets me sync across devices, keeps history (which gives me confidence to press delete which is very important), and i can use pre-commit hooks to run vale to enforce some limited linking behavior. ie some terms i want to ensure i also setup as a back link any time i write them down. It is also somewhat trivial to have bots interact with the markdown files and commit.

My main hugo site contains recipes. it is a submodule now, but was just part of the same repo at first. Another is a manual for how to build my home lab from scratch. I consider these sites part if my “Express” in Tiego Forte’s CODE method. CI builds and deploys them, and then i scan a qr code i put on my fridge to jump to the recipes website quickly. I can also (manually) print the sites to keep a meat space copy of this crucial and well structured info.

Renovate keeps some stuff up to date. Specifically it keeps hugo/its dockerfile and the standalone python/go apps i have written for myself and others (and stored in separate repos) up to date. I do keep codesnippets in my obsidian vault, which renovate does not help with because those are small one/two liners.

What else… imo a monorepo is better for retrieving information than if you split it out. Forgejo search does not work across repos, and imo even if you used a provider that does, it is always more complex to have to look in many places vs 1. I would advise you try putting all your personal scripts in one place rather than spread them around. I only give my apps a seperate repo when i am ready to share them with others and i need that clear boundary for access.

I also recommend writing down things in your daily note first, and only moving or putting structure around it after you need to retrieve it. Basically reduce the friction with entering info in (also remember to summarize info, dont dump whole articles and such in) and allow yourself grace and time to retrieve it.

I am interested in reading more about what Tezka means. Please do share.

I think i can relate to your goals and am personally focused on similar work in an effort to make my own life a little more bearable. my efforts are more focused on executive function and how to integrate this into my life seamlessly vs llm/conversational ai. i have been playing around with conversational ai, but i currently lack the psychological understanding which is needed to do this right. i look forward to hearing more from you.

my immediate (ok, i have been working on this all day) thoughts

• as other have mentioned, i like quirky. I would want them to show some flaws. idk what exactly, but i think it would be off-putting to be overly clinical or “perfect”
• i would be more comfortable interacting with Tezka in a more private environment such as a matrix room vs a more public comm like this.
• i like the “relational repair” aspect. my own shortcomings here is something that has been made much clearer to me recently. I imagine them asking me if i have reached out to my relations, and give me some personalized advice on how best to approach the person. If the interaction with the person did not go well, then i imagine them helping me through it in a positive way, preparing me to try again next time.

To expand with my personal experience, I self host a synapse server partly for the reason that i want my children (aged 8-14 now) to have a communication platform they can access to get ahold of me with out requireing a sim card. I do not federate, and i do not allow account sign ups. That keeps a pretty isolated instance while still allowing everyone on that homeserver to be able to talk to each other.

I help them get Element setup on each device. I dont think this is overly complicated, but i am sure i am a horrible judge of complexity… They have to enter the url of the server, then their password, then they need to scan a qr code/verify from an existing device. Or, they need to enter a second passcode to verify their identity. I help them keep those secrets in bitwarden, so imo, that complexity is an opportunity to explain some opsec and encryption!

For keeping track of tasks on my projects i use todo txt. For each of my projects will drop a file named todo.txt in the root. each line is a task, and i order them based on priority. I can walk away from it and when i start working on the project again, i have an simple way to see the list of tasks i have laid out for this project.

http://todotxt.org/

I personally find it less useful to see the “big picture” of all tasks, and this lets me focus on the details of my projects without forcing a bunch of structure.

I am using Mistral 7b Instruct for text summary and some light “assistant” type chatting for the last several months. I have been pleased at how accurate it is for my needs, especially given it’s size.

I recall alot of trial and error to find models that were compatible with the version of llama-cpp-python that oobabooga uses (at any given time). GGUF should have made the model format (and therefore model selection) more simple, but i imagine there are still nuances that make it more difficult than it should be to find a working model for a noob.

Best of luck, let us know how it goes

VS Code’s extension system makes it pretty easy to build your own code snippet extension. I use my own private extension to easily “generate” different types of markdown files (ie readme vs a troubleshooting guide) from my personalized snippets.

I agree that data staleness is a limiting factor. Depending on your needs and technical proficiency you could use use their zimit service (limited in the number of links it follows). The zimit tool is oss and on github, so you can run the it yourself to keep the sites you are interested in up to date in your local kiwix

While not a solution right now, I just want to add that the general transit feed spec aims to solve the data interoperability of different transit systems. The transit system keeps a publicly accessible zip file up to date, and then anyone can pull/parse the schedule/prediction data in a consistent way across transit systems. I know in the us adoption is slow, with vendors prefering to build their own walled gardens and transit agencies lacking the vocabulary or skills to advocate for more open data/tools