MADE TO GROW · New indie services from Korea and beyond
Discover new Korean services, AI tools and open-source developer tools you can try today.
EDITOR'S FIELD NOTES
This week, we look at services with different uses, from comparing products while shopping and editing photos to simulating robots and exploring developer tools.
01While shopping, you can find and compare similar products from other stores. The results appear in a sidebar on the original page, giving you a clear way to compare them.
Explore service →
02You can adjust the background blur of a photo in your browser and compare it before and after editing. You can then download the result as a still image.
Explore service →
03You can test robotic arm movements on the web and recalculate trajectories based on collision avoidance settings. It also shows how to import and run a demo project.
Explore service →
SIGNAL FINDER
Browse by category.
Filter by the tags that interest you.
SITE CAPTURE
flintA lightweight package manager and build system for Linux developers who want to manage C/C++ dependencies through Git and automate compilation with a single JSON configuration file.
SITE CAPTURE
phpEZA lightweight framework for developers building REST APIs on shared LAMP hosting or in simple PHP environments, providing routing, ORM, serialization, and session management in one file.
OPEN TO STARTS
Your service can still be a work in progress. If someone else can open it, you can share it here.
Share the need, curiosity or learning that led you to build it.
Sharing starts a conversation. Feedback and inspiration can help shape your next version.
Open to first-time makers, people building with AI, individuals and teams. We check the link and basic information.
WHY RAIDERS
Someone's first version can inspire another person to start. Share, learn and build your next version.
MADE SOMETHING?
SITE CAPTURE
metisA coding agent that helps developers working on AI and LLM coding tasks carry exploration, memory, execution, and verification forward in a repository or directory.
SITE CAPTURE
DataZenA local-first AI workspace for developers who query, analyze, and automate multiple databases. It provides natural-language SQL, error diagnosis, EXPLAIN analysis, charts, and workflows in one desktop app.
SITE CAPTURE
movesafe-windowsA read-only scanner for Windows users who want to check whether moving a folder could break automations or programs. It examines shortcuts, scripts, scheduled tasks, and other items that refer to the existing path.
SITE CAPTUREA tool for developers who want to add a type-safe backend to an existing app without REST boilerplate. Write schemas, server actions, and authentication in TypeScript files in the typebase folder, then call them from the frontend like local functions.
SITE CAPTUREA free service with 16 tools for development, work, and everyday tasks that run quickly in the browser and handle text and image conversion and calculations.
SITE CAPTURE
PageRivetA desktop program designed to create and edit static web projects with AI clients, providing project path restrictions and dedicated schema validation.
SITE CAPTURE
TokenPressA formatter for developers who want to reduce input tokens in code sent to AI agents. It favors tokenizer-efficient representation over human-readable formatting and does not write results that fail validation.
SITE CAPTURE
ko-piiA Python library that detects Korean PII and reversibly pseudonymizes it for developers seeking to reduce exposure of personal information in public documents or RAG and LLM pipelines.
SITE CAPTURE
cc-gemini-rewriteFor users who struggle to find conclusions and next steps in Claude Code's technical answers, it adds an LLM rewrite directly below the original text on screen.
SITE CAPTURE
luna-chat-coderAn agent skill and repository template for developers who want to work on real GitHub repositories through ChatGPT Web conversations without a local coding agent or tunnel.
SITE CAPTURE
fluent-koreanAn output-style plugin that gives Claude Code users working with Korean instructions and results clear, natural phrasing, with 2 configurations for coding and non-coding use.
SITE CAPTUREVisualize an existing schema as an ERD, export edited designs as SQL for multiple DBMSs, and manage rule checks, change history, and document generation in one place.
SITE CAPTURE
myceliumA tool for developers who want to retain important knowledge and context across AI sessions. It organizes sessions and supports automatic tagging and knowledge extraction.
SITE CAPTURE
Korean-llmA PyTorch-based project for people who want to build a Korean LLM themselves. It explains the development process from early experiments through v4 and describes model training settings.
SITE CAPTURE
latticedbDevelopers working locally with relationship-focused data and AI/RAG workloads can use one single-file engine for graph traversal, vector similarity search, and BM25 full-text search.
SITE CAPTURE
RamanujanResearchers and simulation developers can write distributed scientific calculations in Python, compile them for the Ramanujan runtime, and run them using idle computing power from various internet-connected devices.
SITE CAPTUREFor developers who need a verifiable token and account ledger, it uses one satoshi UTXO as a namespace root, deterministically replays signed events and a hash chain to compute state, and supports offline verification of raw transactions.
SITE CAPTURE
codecutA rule-checking tool for developers who want to explain project rule violations and fixes to coding agents while blocking only violations that can be verified.
SITE CAPTUREA computing engine for users who model, simulate, and analyze complex systems with MATLAB syntax. It is available through a CLI, a collaborative desktop app, and a web browser, and supports automatic GPU acceleration.
SITE CAPTURE
physical-ai-safety-evalA tool for teams evaluating whether actions proposed by AI agents operating laboratory or factory equipment are permitted under declared hardware and deployment conditions.
SITE CAPTURE
weirA tool for development and security teams that want to use OpenTelemetry traces already emitted by AI agents to check in CI whether sensitive data reached an unauthorized destination.
SITE CAPTURE
RealDiffRealDiff runs the same tests before and after a pull request and compares method arguments and return values to find runtime behavior changes that ordinary source review may miss.
This directory lets you find AI agents, MCP servers, and agent skills in one place. You can browse categories and popular tools to explore what is available.
Explore service →