Open-source Voiceflow alternatives

Dify is a platform for building applications on top of large language models. Instead of wiring together prompts, retrieval code and model APIs by hand, teams assemble AI workflows, knowledge pipelines and agents in a shared visual workspace, then move them from prototype to production without changing stacks.

The product covers a workflow studio for agentic flows, a knowledge pipeline that prepares searchable knowledge bases for retrieval-augmented generation, model management across many providers, and a marketplace of tools, models and integrations. Observability integrations such as Opik, Langfuse and Arize Phoenix help trace and debug runs once an app is live.

Dify comes in a few editions: a community edition you deploy yourself with Docker, a hosted cloud service, and an enterprise edition for private deployments. The repository carries a custom license rather than a standard one, so check its terms before offering Dify as a service to others.

Langflow is an open-source platform for building AI-powered agents and workflows. Developers assemble flows in a visual authoring interface and can then deploy each flow as an API or export it as JSON for use in Python applications. It is written in Python and released under the MIT license.

The visual builder is paired with source-code access, so any component can be customized in Python, and an interactive playground lets you test and refine flows step by step. Langflow can orchestrate several agents with conversation handling and retrieval, works with the major LLMs and vector databases, and can expose flows as an MCP server so they become tools for MCP clients. Observability integrations include LangSmith and LangFuse.

You can install the Python package locally with uv, after which it serves the app at a local address, or use Langflow Desktop for Windows and macOS, which bundles its dependencies. It suits developers and AI teams prototyping retrieval and agent workflows who want both a drag-and-drop canvas and the freedom to write code.

Botpress is a platform for building chatbots and AI assistants powered by large language models such as OpenAI's GPT. Its Botpress Cloud product is the main way to build and run agents, and this repository holds the open-source parts that surround it. It is written in TypeScript and released under the MIT license.

The repository contains the public integrations on the Botpress Hub that Botpress maintains, the developer tools for Botpress Cloud including the CLI, SDK and API client, examples of bots written as code with the SDK and CLI, and plugins for Botpress Studio. Developers can create their own integration from a template using the CLI and publish it to the Hub without forking the repository.

Contributions are welcome through pull requests and issues for the code in the repository, while Discord is suggested for faster responses about Cloud issues. On-premise Botpress version 12 is maintained in a separate repository, which is where problems with that version belong.

Typebot is a chatbot builder released under a Fair Source license. It lets you create conversational flows visually, embed them in web or mobile apps, and collect the results as they come in. The building blocks are meant to adapt to many business cases such as lead capture, forms and support triage.

The editor offers more than 30 blocks across bubbles for text, images, video, audio and embeds, inputs for email, phone, buttons, dates, files and Stripe payments, logic for conditions, redirects, scripts and A/B tests, and integrations with webhooks, OpenAI, Google Sheets, Google Analytics, Meta Pixel, Zapier, Make and Chatwoot. Themes cover fonts, colors and custom CSS, and analytics show drop-off and completion rates, with CSV export.

Bots can be shared on a custom domain or embedded as a container, popup or chat bubble using a native JavaScript library. The app is built with Next.js, TypeScript and Tailwind CSS. An official managed service is available, and the project can also be self-hosted. APIs are provided for developers.

Rasa Open Source is a machine learning framework for automating text-based and voice-based conversations. It provides natural language understanding and dialogue management, so developers can build chatbots and voice assistants and connect them to channels such as Slack and Facebook.

Rasa's README states that this open source edition is now in maintenance mode. The vendor directs new work toward Hello Rasa, a browser playground for prototyping AI agents, built on the CALM engine, which pairs a language model that interprets the user with business logic that enforces rules. Agents can be exported to the Rasa Platform for production.

The framework is written in Python and licensed under Apache-2.0, and its repository topics reference NLU, spaCy and conversational agents. Teams already using the classic intent-based approach can keep running it on their own infrastructure, while new projects may want to review the vendor's newer products first.

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.