Build and deploy AI voice agents at scale | Paid | - **Multi-Provider Stack**: Vapi lets developers choose from many STT, LLM, and TTS providers (e.g., OpenAI GPT‑4, Anthropic Claude, Gemini, Deepgram, ElevenLabs) and mix them to suit performance, cost, and voice quality. You have full control over each component in the voice pipeline.
- - **Flow Studio Visual Builder**:Vapi includes visual workflow tools that let you design conversational flows, logic, branching, API calls, and responses in a visual interface or through API configurations.
|
Give your AI agents a budget, not your card | Free tier | - **Policy as Config**: Write your rules in a single `policy.yaml` file. Rules are checked top to bottom, and the first match decides, so you can always tell why a request was approved, denied, or held.
- - **Budgets and Spend Limits**: Set per-transaction caps (`maxAmount`), rolling 24-hour per-vendor caps (`maxDailyAmount`), and an overall daily budget per agent. This stops a runaway loop from draining your account.
|
A shared visual board for you and your AI agent | Contact | - **MCP Agent Connection**: Connect agent apps you already have, including Claude Code, Codex, GitHub Copilot, OpenCode, Pi, Qoder, WorkBuddy, and Trae. Midmap has no built-in model, so it adds no extra AI cost.
- - **Ask and Run Messages**: Hover over a node to leave an Ask message for discussion or a Run message for a board action. Your agent picks up unread messages the next time you call it in your agent app.
|
AI mock interviewer for system design practice | Free tier | - **Realistic mock interviews**: An AI interviewer reacts to your architecture choices in real time and adapts to your seniority level, so the session feels close to the real thing.
- - **Voice or chat mode**: Explain your design out loud or type it out. Voice lets you practice talking through trade-offs the way you will in a live interview.
|
Shareable docs your AI writes and your team comments on | Freemium | - **AI-written Docs, Sheets, and Slides**: Your AI writes documents, builds decks, and publishes tables. Readers can comment on any line or slide, and they can search, sort, and comment on any cell in a sheet.
- - **Comment-to-Revision Loop**: Readers leave anchored comments in the browser. Your agent reads them, replies, resolves them, and publishes the next version, and you can hand comments over with "@agent" or "Send to agent".
|
Checkout API that lets your AI agent shop real stores | Free tier | - **One API for Many Stores**: Search, carts, checkout, and order lookup work the same way at every supported merchant. You switch stores by changing the `merchant_id`.
- - **MCP Server and REST API**: Connect through 17 MCP tools at `mcp.getagentmall.com` or call the REST API directly. The quickstart includes setup steps for Claude Code and Cursor.
|
An AI agent that makes your phone calls for you | Paid | - **Goal Clarification and Planning**: Tell CALL-E what you need, and it asks about anything missing before it plans the call. You won't waste a call on half-finished instructions.
- - **Confirm Before Dialing**: You see who it will call and what it will ask before anything happens. Nothing gets dialed until you approve the plan.
|
Find and fix failures in your production AI agents | Freemium | - **Live Conversation Scoring**: Sampled production requests are scored pass or fail as they flow through the proxy. You track quality on real traffic, and your app's response time doesn't change.
- - **Failure Modes by Root Cause**: Issues are grouped into named failure modes and ranked by severity and frequency. You see what to fix first instead of scrolling through raw logs.
|
All-in-one AI platform for home care agencies | Contact | - **AI front desk**: Answers calls day, night, and on weekends. It handles new client inquiries, caregiver call-outs, job applicants, and family questions, then logs every call in Hailo.
- - **Human approval controls**: You choose whether Atlas confirms bookings on its own or holds them for staff. Changes to schedules, hires, approved hours, and invoices always go to your team for approval.
|