ツール

MiniMax's official CLI, built for agents: chat with MiniMax models from the terminal and generate images, video and speech, plus speech transcription, image understanding and web search. Works with the international platform. Requires a MiniMax Token Plan subscription.

A CLI and Python library by Simon Willison: imports JSON and CSV straight into SQLite with automatic table creation, runs in-memory SQL queries over files, and supports full-text search and table transformations.

Unofficial Intercom CLI built with Printing Press, covering the full REST API: sync conversations and contacts for offline search, bulk-tag conversations about one incident, see customer overviews and SLA reports, and pull or push help articles. US, EU and AU regions; needs an access token.

Self-hostable long-term memory for agents, offering MCP, a REST API and a web dashboard: semantic search, knowledge graph and automatic memory consolidation. Embeddings are computed locally; choose SQLite, Cloudflare or Milvus as the backend.

Fetches US, Hong Kong and China A-share stock data with zero runtime dependencies: real-time quotes, daily, weekly and monthly candles and search as JSON, falling back across Tencent, Sina and Eastmoney sources. Also runs as an MCP server. Unofficial public APIs, no stability guarantee.

The official W3C conformance checker for EPUB, maintained by the DAISY Consortium: finds issues that break the EPUB 2/3 specs and outputs a report, so self-publishing authors and editors can check books before release. Needs Java; download a release and run it with java -jar.

Local text-to-speech CLI built on the open Kokoro model: batch-converts TXT, EPUB and PDF to MP3 or WAV by chapter, with multiple languages, voice blending and speed control; handy for audio versions of course materials. Needs Python 3.11-3.12 and two model files downloaded first.

A three-stage workflow for math modeling contests like MCM/ICM and CUMCM: analysis, solving and plotting in Python or MATLAB, and a Word (optionally LaTeX) paper, with stage-check subagents and OpenAlex plus AnySearch literature search. Generated papers are for reference only.

Adapts an explanation to its audience, from a 5-year-old to a high schooler, college student, parent or executive, adjusting vocabulary, analogies, tone and depth. Useful for teachers, parents and explaining expert topics to laypeople. No account or extra software needed.

Higgsfield's official skills: generate images, video and voiceover from a single prompt for product shots, e-commerce hero images, YouTube thumbnails, brand guidelines and narrated explainers. Requires the Higgsfield CLI and a signed-in account; generations use account credits.

Command-line reference and bibliography manager: add papers by DOI with metadata fetched automatically, search by author, title or tag, and import or export BibTeX. Each entry is a readable YAML file that agents can read and write easily; a web UI is included. Needs Python.

Recommends daily papers from arXiv and Semantic Scholar by research interest, reads them and writes illustrated Obsidian notes and a paper graph; can also search venues like CVPR and NeurIPS. Needs Python 3, Obsidian, a vault path and an interests config; the web app needs an Anthropic API key.

From Harvard Medical School's Zitnik Lab: one MCP connecting 1,000+ scientific tools and databases for drugs and targets, genes and proteins, clinical trials, FDA data and PubMed, for biomedical and drug research. Runs with uv; some sources need API keys; medical conclusions need expert review.

MathWorks' official server that lets agents start your local MATLAB, write and run scripts and unit tests, and check code style and potential errors, for computing, simulation and data analysis. Needs a licensed MATLAB R2021a+ and the downloaded server binary.

Translates a video's SRT subtitles into other languages and generates AI voice lines synced to the timings, producing translated subtitles and dubbed audio tracks. Needs Python, FFmpeg and Google Cloud, Azure, DeepL or ElevenLabs API keys; configure the ini files, then run python main.py.

Turns secondary-school math and science problems into teaching materials: interactive geometry solution pages, 3D molecular views of chemical reactions, and math explainer videos with Chinese voiceover and bilingual subtitles (needs a Zhipu GLM-TTS key). Requires Python sympy.

Lets agents read and write your local Obsidian vault directly: search notes, append to daily notes, tidy tags and properties, and summarize reading or research notes by topic. No need to open Obsidian or install plugins; access is limited to the vault and can be read-only. Needs Node.js 20+.

Econometrician Pedro Sant'Anna's academic Claude Code setup (fork the repo to use it): Beamer/Quarto lecture slides, paper review and mock refereeing, R/Python analysis and replication packages, with specialist subagents and quality gates. Needs Git and Python; slides need XeLaTeX and Quarto.

Uses the Qdrant vector database as a semantic memory layer for agents: store information and retrieve it by meaning, connecting to a remote instance or a local path, with FastEmbed generating embeddings by default. Maintained by Qdrant.

Chinese-English translation and word lookup in the terminal: one command shows definitions, phonetics and examples from iCiba, Youdao and an LLM. No API key needed (built-in free LLM proxy), or use any OpenAI-compatible model. Needs Node.js 20+; queries are sent to these online services.

Batch-normalizes audio and video loudness to standards like EBU R128, with presets for podcasts, music and streaming video; handy for evening out course recordings, podcasts and videos before publishing. Needs FFmpeg and Python 3.10+.

Connects LLMs to ROS and ROS 2 robots: publish and subscribe to topics, call services and actions, set parameters, and read sensor and robot state, without changing robot code. The robot side needs rosbridge running.

Learning plugin for students and self-learners: /learn a topic to get a first-principles knowledge graph; it quizzes you before explaining, a separate agent blind-grades your free recall, and /review schedules FSRS spaced repetition. Progress stays local as JSON; needs Python 3.

Two-stage paper skills: planning studies the style of your target preprint server (e.g. PhilArchive, arXiv), finds gaps in the literature and scores a seven-dimension mock review; writing drafts and checks each chapter from the outline. Suits philosophy and interdisciplinary work; needs Python 3.