Open-source Kore.ai alternatives

Dograh is an open-source platform for building voice AI agents that can make and receive phone calls. It describes itself as a self-hostable alternative to Vapi and Retell, and promises full code transparency with no vendor lock-in. Agents are designed in a visual workflow builder and can be tested quickly before going live.

The platform supports bring-your-own-key setups across speech-to-speech models or a pipeline of language model, speech-to-text and text-to-speech providers, including local models. It is MCP-native, so AI coding assistants can help design and edit agents, and it includes telephony support for inbound and outbound calling, with Asterisk ARI among its topics. It is written in Python and builds on the Pipecat framework.

Dograh is released under the BSD 2-Clause license and can run on premises or in a hosted cloud, with the vendor operating an app site. It suits support, sales and operations teams that want to automate calls while controlling data and provider choice.

WebWhiz lets you build an AI chatbot that knows your product by training ChatGPT on your website's data. You enter your website URL, WebWhiz fetches and prepares training data, builds the chatbot and gives you a short script tag to embed it on your site. It is aimed at small businesses and support teams that want instant answers for customers without writing code, and the project describes the builder as no-code.

The core features listed are easy integration, data-specific responses, regular data updates, a no-code builder, chatbot customization, fine tuning and offline messages. The FAQ in the README explains that the site is crawled once a month by default, that only public data available to search engines is scanned, and that plans have limits on projects, pages and tokens. When the token limit is exceeded, the chatbot stops generating AI responses and returns a predefined message.

The repository is written in TypeScript, topics include self-hosted, and the code is licensed under AGPL-3.0. A hosted version is available at webwhiz.ai, so you can either use the service or run the code on your own infrastructure.