Inbound and outbound calling
Each workspace comes with a phone number that an agent can answer or use to place calls, keeping the same agent available in both directions.
Kelam
Freemium
Kelam gives AI assistants a phone number for making and receiving calls. It supports browser-based agents and coding-agent workflows, with live transcripts, recordings, extracted call facts, and English, Spanish, and French voice conversations.
What is Kelam?
Kelam gives an AI assistant a workspace phone number for making and receiving calls. It is designed for tasks involving businesses and people who may only be reachable by phone, including calling several numbers, navigating hold queues, answering an inbound line, and collecting information from conversations.
A user can describe the job in natural language through Kelam’s browser Builder or add Kelam to a coding-agent workflow. After a call, Kelam returns the recording, transcript, and requested facts as data, while the same number and agent can be used for inbound and outbound conversations.
What can Kelam do?
Natural-language agent setup
Users describe an agent or task in a sentence. The browser Builder can create and deploy agents, while coding-agent users can install the Kelam skill or CLI workflow.
Batch calling and list research
Coding-agent workflows can call numbers from lists such as CSV files, ask consistent questions, and return structured results such as availability, price, budget, or a short reason.
Live call visibility
Kelam identifies the number it is about to dial and provides a transcript while the call is in progress, so users can follow what the agent is doing.
Call records and extracted facts
Completed calls return a recording, transcript, and the facts requested in the task. Call history can also be queried for summaries, outcomes, costs, and reporting.
Three-language conversations
The agent speaks English, Spanish, and French, and the source examples describe switching languages during a conversation when the caller does.
Use Cases
“Research local services”
Ask Kelam to call locksmiths, garages, tyre shops, rental desks, vets, plumbers, or restaurants and compare availability, prices, timing, or booking conditions.
“Handle a business phone line”
Configure an inbound agent to answer a salon, shop, clinic, or front desk, collect caller details, provide operating information, book appointments, send confirmations, or take messages.
“Run outreach and follow-up lists”
Give a coding agent a CSV of leads, no-shows, suppliers, or clinics. Kelam can call each entry, ask the same questions, and return a CSV or spreadsheet-ready set of answers.
“Manage urgent or time-sensitive calls”
Use the agent to contact an airline after a cancellation, find a same-day appointment, locate an emergency service, or identify the fastest available provider before deciding what to book.
“Review and improve call handling”
Query call history for overnight summaries, complaints, voicemail rates, spending, or recurring questions, then describe a correction so the agent can be redeployed while the previous version remains callable.
Frequently Asked Questions
How do I set up Kelam?
You can sign in to the browser Builder and describe the agent you want, or install the Kelam CLI and skill through a coding agent. The documented setup supports Claude Code, Cursor, and Copilot; the source also describes a Claude Code plugin.
Can Kelam make and receive calls?
Yes. A workspace includes a phone number, and the same agent can place outbound calls or answer inbound calls on that number.
What do I receive after a call?
Kelam returns the call recording, transcript, and the facts requested in the instruction as data. The examples also show summaries, CSV-style results, and reports based on call history.
How is calling charged?
The documentation says talk time is billed by the second in cents per minute and capped per call. An unanswered call is free, browser testing costs nothing, and each call records its exact cost. The available source does not provide plan prices or limits.
Which languages does the agent speak?
The product source identifies English, Spanish, and French, and says the agent can switch languages mid-conversation when the caller does.
Quick Facts
- Category
- AI voice agent and phone automation
- Primary workflows
- Inbound calls, outbound calls, batch calling, and call reporting
- Interfaces
- Browser Builder, CLI, and coding-agent skill
- Languages
- English, Spanish, and French
- Call outputs
- Recording, transcript, and requested facts
- Billing basis
- Talk time billed by the second; exact cost recorded per call
Kelam Traffic Analysis
Traffic data is for reference only.
- Domain Rating
- 4
Kelam Alternatives
ThunderPhone
thunderphone.com
ThunderPhone is an AI phone agent platform for building, testing, and deploying voice agents for inbound, outbound, and web or app-based calls. It is aimed at teams that need production call handling with telephony, language support, and workflow integrations in one stack.
Termphin
termphin.dev
Termphin is an Android SSH client for connecting to existing servers, with persistent remote sessions that can be resumed after network drops or a locked phone. It combines terminal access with SFTP, SSH keys, port forwarding, snippets, and support for AI coding-agent workflows.
appdesigns
appdesigns.click
appdesigns is a browser-based editor for creating App Store and Google Play screenshot sets from uploaded app screens. It supports exact store canvas sizes, device frames, text and backgrounds, with an optional MCP workflow for generating editable sets from coding agents.
VDF AI
vdf.ai
VDF AI is an enterprise AI agent orchestration platform for coordinating agents, models, tools, retrieval, and workflows under centralized governance. Run it as a managed cloud service or deploy it in a private cloud, data centre, sovereign environment, AWS account, or air-gapped infrastructure.
Dograh
www.dograh.com
Dograh is an open-source, self-hostable platform for building and deploying production voice agents, connecting telephony, speech, language models, text-to-speech, workflows, and observability on your infrastructure or its managed cloud.
TAMA
madebyrodolfo.com
TAMA is a desktop app for practicing Japanese through realistic voice or text conversations. It provides session feedback, saves useful vocabulary to spaced-repetition flashcards, and supports local models or user-supplied API keys.