Ask HN: What are tools you have made for yourself since the advent of AI?

Would have made them without UI with a bit more elbow grease invested in web-searching for some examples, maybe even a StackOverflow question.

Generally, I'm not a fan of LLMs and their social effects.

- https://blunders.ai : Chess improvement app

- https://fretwork.ai : Freelancer management app (CRM/Billing/etc)

- https://validity.ai : Provide agents the ability to check the UI code it made (w/out needing to run through your full app)

- Save money on groceries + meal planning. This has probably saved hundreds if not $1k+ for our household at this point (some details here: https://x.com/ryanlanciaux/status/2063604299590939042)

- Orchestration / Starter Kit / Chat : Tool to help me manage multiple agent sessions at once. Some details on this one here https://x.com/ryanlanciaux/status/2063976049537417408

I collect song metadata from various places (genre, instruments, track credits, rating). I also scrape charts by year, genre etc.

Then I run an ETL job on the json data I have downloaded, pre-building queries for extremely fast lookup tables. This gets saved to Duckdb, which is used by my go web ui/api.

It's very early days, and I only spend one or two hours a week on it, but right now it's amazingly useful. It had roughly 80k song metadata. To preview the suggested songs I ended up building a very cut-down YouTube music player, except that the playing song has all the metadata right there, and everything is a link that can take you to the artist, composer, instrument, genre, album etc. It's a great way to "wander through your collection".

Unfortunately this is only useful to me, because I targeted the music I listen to.

Next step is to download lyrics and extract song meaning, keywords etc. Then use MusiCNN, (or CLAP,OpenL3, HTSAT) to extract embeddings. Finally train my own model for nearest-neighbor retrieval based on a mix of metadata, giving the user the ability to tune it on the fly.

This was inspired by a karpathy tweet [0] and the prototype created using another tool of mine: The LLM Plugin Generator plugin (essentially a curated collection of plugins for simonws llm cli as a few-shot prompt)

The llm-model-gateway companion plugin lets you serve models from the LLM cli as a an openai API. This allows you to use saved consortiums in your various clients as if they where a regular model. Bringing massive parallel reasoning to any workflow.

It occured to me at some time that an collection of parallel LLMs was not really a consortium. A consortium is a group of organizations. A group of groups. To rectify this I added for actual consortiums, where each member of an llm-consortium can itself be a consortium of models. e.g.

llm consortium save cns-glm-n3 -m glm-5.1 -n 3 --arbiter mercury-2

llm consortium save cns-k2-n3 -m kimi-k2.6:3 --arbiter mercury-2

llm consortium save cns-meta-glm-k2 -m cns-k2-n3 -m cns-glm-n3 --arbiter cns-k2-n3

Yes, even the arbiter/judge can be comprised of a consortium of models, bringing parallel reasoning to the task of judging parallel reasoning chains.

Consortiums can also now contain groups of specialists. These custom user-defined expert characters address the prompt from a different perspective. And a Westworld style Attribute matrix can be randomized to inject some more entropy into the process.

[0]https://xcancel.com/karpathy/status/1870692546969735361

Some other llm plugins I vibe coded:

classifai generates labels with approximate confidence derived from logprobs

llm-alias-options saves inference parameters such as reasoning effort with a model alias. (good for setting the provider in openrouter or creating a consortium of high temperature models)

llm-prompt-json adds a --json flag to return the llm logs object (good for getting conversion_id, or reasoning output in scripts)

llm-jina adds support for all jina AI specialised models and tools like web fetching, embedding and reranking.

And the inverse as well, of course.

Runs on a raspberry pi that I was otherwise using to take backups periodically… has been working pretty good honestly.

I also built a program that fills/submits my time reports, and does the same for all of my subordinates - then signs them off… Saves everyone like 5 minutes if we remember to do it, or 12 minutes and frustration if we’re reminded by HR about it (which happens because who the hell cares about time reports?)