Packages

Accessibility testing engine (axe-core) and enterprise API (axe DevTools) for automated detection of WCAG compliance issues in web applications, with REST API for CI/CD integration and reporting.

Open-source, typo-tolerant full-text search engine written in Rust with an official MCP server, offering instant search results, faceting, filtering, and hybrid semantic+keyword search.

French AI company offering efficient, open-weight LLM models with strong performance-to-cost ratio. Mistral Large (flagship), Mistral Small, and specialized models for code, math, and embeddings via API and self-hosting.

Together AI provides high-throughput, cost-effective inference for 100+ open-source LLMs including Llama 3.x, Mixtral, Qwen, DeepSeek, and Code Llama. Uses an OpenAI-compatible API (same endpoint format, same client libraries), making it a drop-in alternative for agents using OpenAI SDKs. Supports chat completions, text completions, embeddings, image generation, and fine-tuning. Popular for teams wanting open model access without vendor lock-in.

Managed vector database for storing and querying high-dimensional embeddings at scale, enabling semantic search and retrieval-augmented generation (RAG) for AI applications.

Qdrant is a high-performance open-source vector database and search engine written in Rust, designed specifically for AI and machine learning workloads. It stores high-dimensional embedding vectors alongside arbitrary JSON payloads and enables fast approximate nearest neighbor (ANN) search with rich metadata filtering. Qdrant supports dense vectors, sparse vectors (BM42), and multi-vector configurations — enabling hybrid search that combines semantic similarity with keyword relevance in a single query. Available as self-hosted (Docker/Kubernetes) or fully managed via Qdrant Cloud, with an official MCP server for direct AI agent memory integration.

Service discovery, service mesh, and distributed configuration management API. Enables services to register themselves, discover other services, share configuration via KV store, and health-check each other.

Enterprise feature flag management platform with REST API for creating, toggling, and targeting feature flags across environments, supporting gradual rollouts, A/B testing, and kill switches.

Free, open-source weather API with no API key required, providing hourly and daily forecasts, historical data, and marine/air quality data from multiple numerical weather prediction models.

Open-source, typo-tolerant search engine designed as an Algolia alternative, with a simple REST API, vector search support, and Typesense Cloud for managed hosting.

Amazon Simple Queue Service — a fully managed message queuing service for decoupling and scaling microservices, distributed systems, and serverless applications.

Affordable cloud platform (now Akamai Cloud) offering VPS, managed Kubernetes, managed databases, and object storage with a well-documented REST API, backed by Akamai's global CDN network.

GitHub's CI/CD automation platform with a REST API for triggering, monitoring, and managing workflow runs, artifacts, secrets, and runners programmatically from agents.

Terraform Cloud (now HCP Terraform) provides managed state storage, team collaboration, policy enforcement, and CI/CD integration for Terraform infrastructure-as-code. The REST API exposes workspaces, runs, state files, variables, and policy checks — enabling agents to trigger infrastructure provisioning, query resource state, manage variables, and monitor deployment status. Industry standard IaC platform with the largest provider ecosystem (3000+ providers).

Weather data API providing current conditions, forecasts up to 14 days, historical data, astronomy, time zone, and sports weather via a clean REST interface.

Firecrawl converts any URL or website into clean, LLM-ready markdown. It handles JavaScript-rendered pages, bypasses common anti-scraping measures, converts PDFs and other formats, and returns structured content that agents can immediately use without HTML parsing. Includes crawl (multi-page), scrape (single-page), extract (structured data with schema), and search endpoints.

Serverless cloud compute platform for running Python functions on demand with GPU acceleration, enabling ML inference, training, and data processing without infrastructure management.

Geocoding API built on open data sources (OpenStreetMap, GeoNames, etc.) that converts addresses to coordinates (forward) and coordinates to addresses (reverse) with global coverage.

Slack's platform API for sending messages, managing channels, building bots, and automating team workflows, with multiple official MCP servers for agent integration.

Serverless REST APIs for Redis, Kafka, and QStash (message queuing) with per-request pricing — designed for edge functions and serverless environments where persistent connections aren't possible.