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
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.
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
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
tareA tool for users who want to understand why they reached a Claude Code usage limit and where tokens went by project and model. It reads session logs already on the computer to answer natural-language questions.
SITE CAPTURE
experientialIt provides a single control plane and an OpenAI-compatible gateway for agent workflows that use proprietary, open-source, local, and custom models together.
SITE CAPTURE
conductaiIt applies shared policies to LLM, shell tool, and MCP calls for development and security teams operating AI agents. Before sending a request to a provider, Guard checks policy and budget and records decisions such as blocks, warnings, and audits.
SITE CAPTURE
rundownA desktop client that summarizes long Hacker News posts and comment threads and lets users chat about an article or points raised in its discussion.
SITE CAPTURE
Termux-DevA terminal agent for developers who want autonomous AI pair programming on Android Termux or a desktop. It offers Plan and Agent modes, multimodal vision, a live web server, diagnostics, and rollback.
SITE CAPTURE
HardenIt analyzes tool calls locally before execution so development and security teams using coding agents can control risky actions in advance. It also checks software before release.
SITE CAPTURE
singular-liteA Bash and Python engine for teams running multiple autonomous AI coding agents in a software repository. It coordinates parallel work with 3-level scheduling, persistent leases, an audit pipeline, and Git worktree isolation.
SITE CAPTURE
LeadcodeAgencies and contractors working with multiple companies can connect GitHub, Claude Code, and Codex accounts to client-specific macOS workspaces, keeping development environments separate without logging out or switching authentication.
SITE CAPTURE
understudyA scenario-based test framework for developers who want to simulate multistep behavior of conversational and autonomous AI agents and evaluate it through execution traces centered on tool calls.
SITE CAPTURE
provalDevelopment teams that want to use their own models and infrastructure without an external review SaaS can review pull requests and issues on GitHub, GitLab, and Forgejo with an LLM.
SITE CAPTURE
hrdxAn experimental lightweight terminal multiplexer for developers who want to run AI agents such as Codex CLI and Claude Code alongside shells across multiple projects.
SITE CAPTURE
beckonFor Claude Code users who cannot keep watching the terminal, it uses different sounds to signal when an agent finishes, needs a decision, or fails. When running remotely over SSH, it uses the terminal bell and desktop notifications.
SITE CAPTURE
shadok-aiA tool for developers who want to run Claude Code sessions in parallel in separate Git worktrees and view or answer questions and status changes in a browser or Telegram.
SITE CAPTURE
pi-blackA Pi package that helps developers use a Claude Max or Pro subscription in Pi by routing Anthropic OAuth requests through their existing subscription usage.
SITE CAPTURE
Forth MCPFor teams connecting MCP clients such as Claude and ChatGPT to multiple local and public MCP servers, it provides a single address, connectors, per-tool permissions, call auditing, and status monitoring.
SITE CAPTURE
dmxdmx is an open-source engineering tool that manages AI development work in MCP-compatible IDEs such as Cursor, Claude Code, and Copilot as repeatable loops with ordered steps, approvals, and validation rules.
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 →