AI Tools Directory

Pull structured data from any website using 30,000+ ready-made scrapers and managed proxies, without running your own servers. Now has an MCP server so agents can invoke Actors directly.

Turn audio and video into accurate text via API on the Universal-3.5 Pro model (Universal-2 remains available for entry pricing and broader language coverage), with speaker labeling and Speech Understanding, without building your own speech models.

Access GPT and other OpenAI models through Azure with enterprise compliance, networking, and regional data controls. Now offers Global, Data Zone, and Regional deployment types.

One MCP endpoint gives every AI agent you run, across Claude Code, Cursor, or Codex CLI, the same shared memory, email inbox, and connectors, so switching frameworks stops meaning starting over.

Trace, score, and compare LLM outputs to catch quality regressions before they reach production. Closed an $80M Series B at ~$800M valuation in early 2026.

Give your AI agents a real browser in the cloud. Handles the Chromium, CAPTCHA solving, and proxy rotation so your agents can navigate any site without infrastructure overhead.

Add hosted inference through Cerebras’s OpenAI-compatible API, checking the current public model catalog and access limits before you build around a specific model.

Unify vector, full-text, and metadata search for AI applications. Chroma Cloud (GA since August 2025) runs on object storage to keep large-scale retrieval cost-efficient.

Get direct API access to generation, embedding, and reranking models built for enterprise search and retrieval, plus dedicated deployment for regulated environments. Now on the Command A family.

Turn web pages into clean, LLM-ready Markdown for RAG pipelines and agents with the most-starred open-source crawler in its category, free and self-hostable.

Convert speech to text (and text to speech) in real time via API on Nova-3, so developers add voice understanding to their apps with usage-based per-minute billing.

Build rule-based or generative conversational agents for chat and voice that plug into Google Cloud's NLU and generative AI stack, billed per request or session. Increasingly marketed as Conversational Agents.

Build and orchestrate LLM applications and agentic workflows with visual workflow design, RAG, and knowledge-base management, source-available under a modified Apache 2.0 license with 139,000+ GitHub stars.

Design, deploy, and monitor AI agents through a no-code visual builder with built-in QA testing and observability, for embedding AI features into SaaS products without vendor lock-in.

Let your AI agent execute real code in a secure cloud sandbox: spins up in 150ms, runs Python and JavaScript safely, and tears down cleanly when done.

Run FLUX.1, Stable Diffusion, and 100+ image and video models via API with sub-200ms cold starts. Fast enough for production apps, not just demos.

Convert websites into clean markdown or structured data through a purpose-built scraping API for AI applications, with a credit-based subscription and self-hosted open-source option.

Run Llama, Mixtral, and 50+ open-source models at production speed: model-specific token billing with the same SDK you're already using.