LLM Knowledge Bases
Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:
Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.
IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).
Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.
Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.
Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.
Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.
Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.
TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
if you're a performance marketer, here's how I use a custom Claude Cowork plugin to manage Google Ads at @AnthropicAI. it connects to the Google Ads API via MCP, encodes my common paid search workflows into skills, and works on desktop and Dispatch.
New Agent skill: baoyu-youtube-transcript 🎬
Extract YouTube transcripts directly — no API key needed.
✦ Multi-language support
✦ Chapter segmentation
✦ AI speaker identification
✦ SRT & Markdown output
✦ Smart caching for instant re-formatting
Just select the skill and
40K Followers 476 FollowingI’m CEO, bitch.
Building https://t.co/Xd1e237tVD that leaves competitors hopeless.
Building https://t.co/WMbovmcJif
The only Vibe Coding 👇 tutorial you need.
2K Followers 70 FollowingOpen source 2D raster & vector editor that melds traditional layers & tools with a modern node-based procedural workflow. #MadeWithGraphite
80K Followers 7 FollowingBun is a fast, all-in-one toolkit for installing, bundling, running and testing JavaScript & TypeScript. To install: `npm i -g bun`
128K Followers 264 FollowingThe AI Lab behind GLM models, dedicated to inspiring the development of AGI to benefit humanity.
https://t.co/7a5aSCUNcZ
https://t.co/x14hb3klXm
5K Followers 368 Following🦋 INFP; MSc CS (@ZJU_China, Mobile Internet & Game Dev); A mere cog in the vast machine @Trae_ai; @nodejs Collaborator Emeriti; Retired (OI & ACM)er.
7K Followers 297 Following- Currently focused on @Trae_ai IDE.
- Used to be a core developer of open source projects EggJS/CNPM.
- ByteDance Engineer / ex-Alibaba.
331K Followers 65 FollowingWe're sharing/showcasing best of @github projects/repos. Follow to stay in loop. Promoting Open-Source Contributions. UNOFFICIAL, but followed by github
322K Followers 138 FollowingBuilt by Moonshot AI to empower everyone to be superhuman.
@Kimidevs built for developers
⚡️API: https://t.co/XCrgjXAqMw
DC: https://t.co/wBsBTn6Ncc
420K Followers 50 FollowingTypeScript is a language for application-scale JavaScript development. It's a typed superset of JavaScript that compiles to plain JavaScript.
2.2M Followers 433 FollowingAWS is the world's most comprehensive cloud, enabling organizations to accelerate innovation, reduce costs, and scale more efficiently.