Packages

Google's UI toolkit for building natively compiled applications for mobile (iOS/Android), web, and desktop from a single Dart codebase. pub.dev is the Dart/Flutter package registry with a REST API for package metadata, search, and version information.

Topic modeling and document similarity library for Python — train and use Word2Vec, FastText, Doc2Vec, and LDA topic models. Gensim features: Word2Vec.train() for word embeddings, wv.most_similar() for nearest words, wv.similarity() for cosine similarity, FastText for subword embeddings (handles OOV), Doc2Vec for document-level embeddings, LdaModel for topic discovery, TfidfModel, corpora.Dictionary for vocabulary, corpora.MmCorpus for streaming large corpora, similarities.SparseMatrixSimilarity for document retrieval, and downloader API for pretrained models. Classic NLP library for training embeddings on domain-specific text when general pretrained models underfit.

Manages Google Cloud identity and access control — assigns primitive/predefined/custom roles to principals, manages service accounts, configures workload identity federation, and evaluates IAM policies across the GCP resource hierarchy for AI agents automating cloud security posture.

Google's fully-managed enterprise cron job service for scheduling recurring HTTP, Pub/Sub, or App Engine requests on a defined schedule, with configurable retry and timezone support.

REST API for programmatically reading Google Forms structure and responses, and creating or modifying forms, enabling automated survey data collection, response processing, and form management within Google Workspace.

Modern spreadsheet-database hybrid with full Python formula support, granular access control, and a REST API. Grist combines spreadsheet UX with relational database structure — tables with typed columns, formula columns (Python or JavaScript), linked tables, and summary tables. REST API enables programmatic CRUD on Grist documents, making it a structured data store with spreadsheet-style views for human collaboration. Used as a lightweight internal database, CRM, or project tracker with an API for agent integration.

Hashnode — developer blogging platform with a GraphQL API for creating, publishing, and managing blog posts, enabling agents to programmatically publish technical content to the developer community.

Hosted inference for 100,000+ open-source ML models including LLMs, embeddings, image generation, audio, and specialized NLP tasks via a unified REST API. Dedicated Endpoints provide production-grade isolated GPU inference.

Instagram MCP server enabling AI agents to interact with Instagram — posting images and reels, reading comments and DMs, accessing follower analytics, scheduling content, and integrating Instagram into agent-driven social media management and content marketing workflows via Instagram Graph API or unofficial access.

Converts any public URL to clean, LLM-readable Markdown by prepending r.jina.ai/ to the URL. Handles JavaScript-rendered pages, strips navigation/ads/boilerplate, and returns structured text optimized for LLM context. Supports screenshots, link extraction, and streaming. Free for basic use; API key unlocks higher rate limits and advanced features.

Cloud platform for building stateful, long-running AI agents with built-in persistent memory, multi-step task execution, and tool integration — defined via YAML workflows.

Kontent.ai REST and Management APIs for headless content management platform. Enables AI agents to query and deliver structured content, manage content items and types, trigger content workflows, and integrate Kontent.ai into omnichannel publishing pipelines. Kontent.ai supports structured content modeling with strong editorial workflow capabilities.

An open-source educational course and codebase teaching developers how to build production-ready multimodal AI agents that process images, video, audio, and text via a unified MCP server built with FastMCP, Groq LLMs, and Pixeltable memory.

MCP server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through standardized MCP tools and resources.

Luma Dream Machine provides a high-quality AI video generation API with Python and TypeScript SDKs for text-to-video and image-to-video generation.

Open-source LLM observability and analytics platform with full tracing, cost tracking, user analytics, and evaluation capabilities. Lunary captures every LLM call with inputs, outputs, tokens, costs, and latency — and provides a UI for analyzing agent behavior, debugging failures, and running evals. MIT licensed with self-host option. Built for production LLM apps: supports multi-step agent traces, user tracking, and A/B testing of prompts.

An MCP server that gives AI agents full GUI control over remote macOS machines via Apple Screen Sharing, enabling screenshot capture, keyboard/mouse input, application launching, and drag-and-drop — all without installing software on the target Mac.

Lucene-based full-text and vector search built directly into MongoDB Atlas, enabling agents to run semantic and keyword search without a separate search infrastructure.

A self-hosted web UI for managing Nginx servers with real-time monitoring, online configuration editing with validation, SSL certificate automation via Let's Encrypt, multi-server cluster support, and an MCP interface for AI-assisted configuration management.

Open-source uptime monitoring and status page platform with a REST API. OpenStatus monitors HTTP endpoints, TCP ports, and DNS from multiple global regions and provides a public status page for communicating service health to users. REST API enables programmatic monitor creation, incident management, and status updates — making it suitable for agent-driven status page automation. Positioned as an open-source alternative to Better Uptime and Atlassian Statuspage.