SQLite — A Single-File DB for Local Apps
6 min
SQLite is an embedded database that holds a SQL database in a single file. It is one of the most frequently chosen options for local storage in desktop and mobile apps.
7 views
Things I studied and noted down. For courses, see EDU.
Things I studied and noted down. For courses, see EDU.
AI/LLM topics — agents, prompts
HTML, CSS, JS, HTTP, URL basics
TypeScript, Java, Python, Rust
Data structures, Big-O, patterns
React, Next.js, Tauri, Tailwind
Spring, FastAPI, SQL
Claude Code · MCP · Context7 · Figma — overview of AI coding tools
Deployment options and decision criteria
PostgreSQL · Kafka · data strategy notes
Docker, Compose, Caddy, SSH
Windows vs Mac and other dev-environment notes
Cross-platform options compared (Tauri · Flutter · RN)
pnpm, uv, Gradle, Git, regex
KISS · DRY · YAGNI · naming — development philosophy
OAuth · JWT · security fundamentals
Testcontainers, Vitest, pytest
Searching, reading docs, debugging
SQLite is an embedded database that holds a SQL database in a single file. It is one of the most frequently chosen options for local storage in desktop and mobile apps.
7 views
An embedding is the result of mapping text (or images · code) to fixed-dimensional real-valued vectors. On top of the assumption that semantically close items sit close in the vector space, search · clustering · classif…
5 views
A monorepo keeps the source for many projects in a single version-controlled repository. This article covers what a monorepo is, its history, how far a lightweight setup like pnpm workspaces can take us, and what full-s…
5 views
The LLM market shifts fast. Closed-API and open-weight, English-centric and multilingual, cloud and self-hosted, models specialized for Korean — all sit alongside each other.
4 views
The word "agent" is used in several senses, which is a confusing situation. Script automation is called an agent, and so is the shape of an LLM calling tools.
4 views
Aside from in-IDE assistants, AI coding tools in terminal CLI form are growing on their own track. The motivations are friendliness with shells, SSH, and CI; script automation; and a lighter interface.
Around the time Cursor went GA in 2023, IDEs where "AI is the main interaction" multiplied fast. Various attempts have been made, either as VS Code forks or new editors. Capability evaluations change quickly with time,…
As AI coding assistants multiplied, the convention "write the project rules and context in a single file" took root. Tools differ slightly in name and location, but the intent is similar.
There are places where you want external behavior to run before or after an LLM agent's tool call. Auto-formatter execution, change watching, logging, policy validation, secret-leak blocking — that kind of work.
When a large task is handed to one LLM instance in a single shot, the context fills quickly and responsibility blurs. Subagents are the pattern of slicing a task into smaller units and delegating each to a separate mode…
Claude Code is Anthropic's terminal-based coding assistant CLI, released in February 2025 (research preview at the time). It later moved to general availability and gained features like IDE integration, GitHub Actions,…
The Agent Development Kit (ADK) Google released in 2025 is an open-source framework for building LLM-based agents and multi-agent systems. It assumes integration with Vertex AI but stays relatively neutral on models and…
Attempts to feed information from design tools into a code-writing LLM are growing. When a designer's screen is shown to the LLM and components, tokens, and layouts are translated into code, Figma occupies the largest p…
The training-data cutoff of an LLM never quite matches the latest. Library docs and API specs change often, and the model answers with old information confidently. MCP servers and services that expose docs in an LLM-fri…
If MCP is the standard, the clients are the entry points that actually expose it to users. Multi-client environments, where multiple clients share the same server simultaneously, are the reality.
The Model Context Protocol (MCP) is a protocol for connecting LLM clients to external data, tools, and prompts in a standardized way. Anthropic released it in November 2024 and other AI tools and IDEs adopted it quickly…
The LLM market shifts fast. Closed-API and open-weight, English-centric and multilingual, cloud and self-hosted, models specialized for Korean — all sit alongside each other.
The word "agent" is used in several senses, which is a confusing situation. Script automation is called an agent, and so is the shape of an LLM calling tools.
An embedding is the result of mapping text (or images · code) to fixed-dimensional real-valued vectors. On top of the assumption that semantically close items sit close in the vector space, search · clustering · classif…
Gemini is the model series Google DeepMind released in late 2023. Multimodal input — handling images · audio · video · code alongside text — and the very long context that came in with 1.5 are the often-cited features.
A prompt is closer to the design of an input interface itself than just a string sent to an LLM. Message structure · reasoning patterns · sampling parameters · security all entangle at once.
RAG (Retrieval-Augmented Generation) is an approach to supplement an LLM's limited training cutoff and memory limits with external knowledge. By separating retrieval and generation, you can handle new material without r…
The trend of running large language models directly on personal computers has taken hold rapidly since 2023. Where there used to be only cloud APIs, the combination of quantization formats like GGUF, inference runtimes…
HTTP is fundamentally a one-request-then-one-response model. It is hard for the server to speak to the client first. In places like chat, notifications, and live updates, the server must be able to push data actively.
When writing an API on top of HTTP, REST is the word that comes up most often. It stands for Representational State Transfer, organized in Roy Fielding's 2000 doctoral dissertation.