

透明性確保とサイト運営への負荷低減を目的とした、エージェンティック検索エンジン
Automatically translated from Japanese by AI

A powerful Markdown editor with WYSIWYG split-screen, CodeMirror integration, bidirectional synchronization, and LaTeX formula support.

llama-cpp-python, which is mainly used to run GGUF local LLM models. It's very convenient, but the setup is quite tedious, so this tool allows you to install the optimal llama-cpp-python for most environments all in one go. Since the main focus is on installing llama-cpp-python, please research and install any other necessary files yourself. It also includes functionality to decide whether or not to create a virtual environment, and after setup, to temporarily (or permanently) download a lightweight model from HuggingFace and test whether it actually works.

Check if dangerous API keys are mixed in code made by AI, just paste it to check. Input is not sent.

A website called "A Better Life" that provides small free tools and practical guides for making daily improvements through sleep, nighttime routines, habits, and more. The design is focused on a streamlined user journey from search → tools → action, rather than miscellaneous content.

Analyze logs smartly with the power of AI! An open-source log analyzer that automates and streamlines anomaly detection and pattern analysis from massive logs, reducing the burden on system administrators.

Free! Combine and extract PDF pages with bookmarks. Works on any device with a browser display. Download ZIP for complete local use. You can also open the URL and use it locally as-is for processing.

外来がん化学療法情報プラットフォームです。主に薬局薬剤師向けのコンテンツとなっています。「この治療、分からない。」を解消するための抗がん剤に特化した情報アプリになります。

Ultra-lightweight HTML AI chat that runs only in a browser - beta version now available I'm not very smart.

Find issues in Analytics Improve with Firebase Confirm results in Search Console

A report creation support tool that automatically generates reference lists and shortened citations in APA, MLA, and SIST02 formats by simply inputting bibliographic information

A tool that detects AI-like clichéd phrases just by pasting an article, usable for self-checking before submission

Paste and detect/clean "invisible characters" that sneak in through copy-paste. Visualize the cause of form rejections. Does not send.

This is an AI chat using a built-in browser LLM. There are no usage restrictions, and you can chat for free as much as you want.

A free tool that aligns scattered fonts, full-width/half-width characters, and position misalignments in PowerPoint materials with one click

This is a multi-stage obfuscation framework. Since it's written in C++ and PHP, it can run on both web and desktop applications.

The free, all-in-one Chrome video downloader.

You can extract white-collar positions from Indeed job listings.

Philosophy Explanation AI Generation App

DICOM (CT, MRI, X-ray, Ultrasound) - whether an entire folder or a single image. Image masking and metadata tag removal, batch saving to ZIP supported. Selectable save formats: DICOM, JPEG, PDF. Completely offline browser-based.

Navily is a career growth service where an AI coach designs a learning roadmap just by hearing your goal and accompanies you every step of the way on a daily basis. An AI companion service for people in their 20s to 40s who want to break free from being "unable to take action."

「これ、もう持ってたっけ?」を防ぐために作った在庫管理ツール。電子部品の型番・数量・保管場所を記録して、二重購入を防ぐ。電子工作ホビイストのためのアプリ。

Don't entrust images to suspicious upload conversion services. WebP→JPG/PNG Convert WebP to JPG and PNG. Unlike upload-type services, images are processed only on your device. Ideal for confidential screenshots and Excel paste operations. 【Operating Environment】Completely browser-based (no registration required). Images are not sent to our servers by design. 【Tags】WebP JPG PNG image conversion browser-based document creation data processing ※Screenshots will be added at a later date

28卒の就活を、最短距離で攻略。

A TODO management and hub tool that uses Markdown as a database. It's finished with a somewhat rich TUI.
A web search function that minimizes reliance on scraping as much as possible. The purpose is to ensure transparency and reduce the load on site operations.
Using Playwright, we perform the following series of steps: input a word in the search box → search → visit the site → temporarily save in memory using the browser's standard HTML download function → remove unnecessary information and save to an MD file → convert MD to JSON.
This is an MCP server, but it can also be used as a CLI tool (command: aw-se).
A summarization feature using local LLM via Ollama is also available. In that case, set the argument to enable Ollama usage. (This will take more time.)
By passing not just the search word but also the search intent, the local LLM will summarize while omitting unnecessary information.
Additionally, for academic papers and similar content, we enable information retrieval using official APIs from arXiv and PubMed. In that case, switch the mode. There are two types: normal web search mode and academic mode.
Also, when the link destination is a PDF, we have exception handling that parses text from the PDF and converts it to MD.
If you want to dig deeper, you can enable the secondary search feature, which allows the local LLM to generate new search words and perform the same process again.
All search results are designed to be stored in a folder created with the search word as the name within the "artifacts/" folder, with everything contained within. Additionally, for reverse lookup purposes, we use a CSV file to leave pinned information stating "this information is located at line 〇 in the file." This eliminates the need to unnecessarily have the AI read the entire text, preventing context pollution in the AI.
※ This is packaged as an npm package. Downloading the source code itself is simple, but please research how to register it as an MCP server on your own. The source code itself has been verified to work. Also, when operating as an MCP server, it is by design that the ollama viewer operates and headless mode is turned off.
Feedback
Share your thoughts, bug reports, or suggestions directly with the developer
Log in to share your feedback
Log in to leave feedback