Инструменты

NVIDIA's open-source LLM vulnerability scanner that probes for prompt injection, jailbreaks, data leakage, hallucination and harmful content, supporting OpenAI, Hugging Face, Bedrock and most REST-accessible models. Scanning cloud models needs their API keys.

Distributed data integration tool and Apache top-level project with 160+ connectors for batch, real-time and CDC sync. Define jobs in config files and run them on the built-in Zeta engine or on Flink or Spark. Requires Java.

High-accuracy retrieval-augmented Q&A over paper PDFs, text and Office documents, filling in citation metadata, checking retractions and attaching traceable sources to answers. Provides the pqa CLI and a Python library. Needs an LLM API key by default; local models can be configured.

Deep research assistant that runs locally with a built-in MCP server: searches arXiv, PubMed, Wikipedia and more over multiple rounds and writes cited reports. Needs Python 3.12+, uv and an LLM (local Ollama or an API key); web search needs SearXNG or similar. Runs take minutes to half an hour.

Terminal tool for exploring and wrangling tabular data: opens dozens of formats including CSV, JSON, Excel and SQLite for filtering, sorting, pivots and frequency counts. --batch mode replays actions headlessly or converts file formats.

Publication-quality matplotlib plotting skill from a Yale PhD student: bar charts, trends, heatmaps and multi-panel figures with consistent fonts, colors and export settings, plus real plotting scripts from papers published in venues like Nature Machine Intelligence. Needs Python.

Say build a harness for this project and it designs a domain-specific agent team, generating subagent definitions, companion skills and orchestration, validates them and keeps evolving them from feedback. Supports workflow orchestration, persistent agent teams and subagent delegation.

Turns outlines or scripts into web slides that present in the browser (not .pptx files), with 36 themes and 15 full deck templates; press S for presenter mode with script and timer. Good for lessons, training and reports. Plain local files; no account or API key needed.

Manage database schemas as code: declare the desired schema in SQL, HCL or your ORM and Atlas plans, lints and applies migrations, and can export existing databases as HCL, SQL or Mermaid ER diagrams. Supports PostgreSQL, MySQL and a dozen other databases.

Converts the output of 100+ commands such as dig, ps, ls and ifconfig, plus common file formats, into JSON so agents can parse it reliably with jq or scripts. Also usable as a Python library.

Offline speech toolkit for Apple Silicon Macs: CLI text-to-speech (including Chinese and voice cloning) and speech-to-text, for voicing lessons and explainer videos or transcribing lectures and interviews, with data staying local. Needs an M-series Mac and Python 3.10+; MP3 export needs ffmpeg.

Query, modify and convert JSON, YAML, TOML, XML, CSV, HCL, INI and more with one selector syntax, editing config files in place or converting between formats, handy for agents handling structured data in scripts. A single dependency-free binary that works much like jq or yq.

Query cloud resources and SaaS APIs live with SQL: plugins map AWS, Azure, GCP, GitHub, Kubernetes and other services to tables you can select from directly, no ETL needed. A single binary with Postgres built in.

Turns Peng Sida's public research-writing notes into a skill: revises abstracts, introductions, methods and experiments of ML/CV/NLP papers from a reviewer's view, checks that each claim has experimental evidence, and runs a pre-submission self-check. Pure methodology, no API key.

Diffusion model inference in pure C/C++: one sd-cli command runs SD, FLUX, Qwen Image, Wan and more locally to create or edit images and short videos, with Metal acceleration on Mac. No cloud needed; bring your own model weights and use a release binary or build from source.

Scrapes web pages into Markdown or structured data, with full-site crawling, sitemaps, web search and interaction with dynamic pages. Maintained by Firecrawl; the cloud needs an API key (self-hosting is possible), and the keyless hosted endpoint only offers scrape, search and parse.

Notion's plugin in OpenAI's official Codex marketplace: uses the Notion connector and hosted MCP to search and update workspace pages, with skills for spec-to-implementation plans, research write-ups, meeting prep and knowledge capture. Codex only; needs Notion authorization.

OpenAI's official Codex plugin with 18 skills to choose, design, build, test and export web charts, maps, dashboards, Gantt charts and UML, using D3, Vega-Lite and Three.js with attention to accessibility and responsiveness. Codex only.

OpenAI's official Codex plugin that uses the local API of the Zotero desktop app to search your library, export BibTeX, insert citations into LaTeX or Markdown drafts, and import new references after you confirm. Requires Zotero desktop.

OpenAI's official life-science skills: 49 skills query public databases such as UniProt, ClinVar, gnomAD and AlphaFold through Python scripts, with a router skill that breaks down questions, normalizes entities and compiles sourced evidence. Written mainly for Codex.

OpenAI's official data analytics skills: data quality assessment, KPI design, metric anomaly diagnosis, dashboards and analysis reports, market sizing and notebooks. Ships with a Codex plugin; some skills depend on its runtime.

OpenAI's official Codex plugin for answering product and business questions with data: metric anomaly diagnosis, KPI design, market sizing, dashboards and reports, notebooks and data quality checks. Connects to data warehouses and BI tools.

OpenAI's official Codex plugin that makes Google Drive the single entry point to search, organize, share and export files, handing Docs, Sheets, Slides and comments to dedicated sub-skills for summaries, edits and new files. Authorize your Google account in Codex.

OpenAI's official Codex plugin that guides sequencing analysis from BCL/FASTQ: QC, RNA-seq differential expression, single-cell, variant calling and metagenomics, favoring nf-core and other public pipelines with reproducible run logs. Checks for local tools first. Research use only.