Ethora: The Open-Source Botpress Alternative You Can Self-Host
Run AI agents on your own servers and your own model, then put them on your website or inside your app. Ethora has an open-source core (AGPL), per-agent model choice including Ollama and vLLM, chat SDKs for web and mobile, an MCP server, and a free cloud plan with no credit card.
The honest short answer
Ethora vs Botpress: the honest short answer
Botpress is a cloud AI agent platform for customer support, built around a visual builder (Botpress Studio), many prebuilt channels and an AI helpdesk. Its documentation says the older self-hosted versions are no longer available for new deployments, so today it runs as Botpress Cloud. Ethora is an open-source chat and AI platform: you can run the whole stack on your own servers, point each agent at a model you host (Ollama, vLLM or any OpenAI-compatible endpoint), and use the same platform for chat inside your own web and mobile apps.
Stay with Botpress if
- Your team designs agents in a visual flow builder and wants to keep doing that
- You need many ready-made channels such as WhatsApp, Messenger, Instagram, Telegram and Microsoft Teams
- A fully hosted service is fine for your data and you want a helpdesk with routing and assignment
Choose Ethora if
- You need to self-host the whole stack, or run it on a dedicated server in your own cloud account
- You want agents on a model you run yourself, so prompts and answers stay inside your perimeter
- You are a developer building chat into your own product: SDKs for web, React Native, iOS and Android, plus an MCP server
Best for: Botpress for visual, multi-channel support agents on a hosted platform; Ethora for developers who want open-source AI agents they can self-host on their own model and embed in their own apps.
Side by side
Ethora vs Botpress: capabilities at a glance
The questions developers ask most when they look for Botpress alternatives. Botpress facts come from its public website, pricing page, integration hub and documentation.
Ethora
How to read this table
Botpress facts are taken from botpress.com, its pricing page, its integration hub, its GitHub repository and its documentation, checked 16 October 2026. Plans and limits change, so check their pricing page for the current state. If something here is out of date, tell us and we will correct it.
Why developers switch
Why teams move from Botpress to Ethora
Both put an AI agent in front of your users. The reasons to switch are about where it runs, which model answers, and whether the agent lives inside your own product.
Botpress
Cloud AI agent platform
Ethora
Open-source chat and AI platform
An honest view
When Botpress is the better choice
We would rather you pick the right tool. Botpress is likely the better fit in these cases.
You build in a visual flow editor
Botpress Studio is a visual builder for agent logic. Ethora has no flow canvas: you configure an agent with instructions, knowledge and tools, in the admin or in code.
Many prebuilt channels
Botpress connects to WhatsApp, Messenger, Instagram, Telegram, Slack, Microsoft Teams and more. Ethora runs on your website and in your own apps, and does not offer those messaging channels.
A support team with a helpdesk
If several human agents need routing, assignment and team analytics around the AI agent, Botpress Desk and the Team plan are built for that. Ethora does not include a ticketing helpdesk.
Build it on Ethora
Everything you need to replace Botpress
The pieces developers use most when they move their AI agents to Ethora.
Self-hosted LLM AI agent
Point an agent at Ollama, vLLM or another OpenAI-compatible endpoint so prompts and answers never leave your servers.
Run it on your own modelSelf-host the platform
Docker Compose, a Helm chart, AWS and Azure Marketplace images, or a dedicated server we run in your cloud account.
Get EthoraAI chat widget for your website
One script tag adds a floating AI chat widget to any site. It loads asynchronously and keeps its styles isolated from your page.
See the AI chat widgetRAG chatbot on your own content
Crawl your website, upload documents, and check which sources each answer used before you go live.
How the RAG chatbot worksPricing
Free plan with 1,000 monthly active users and no credit card, then Small Business at $149/mo and Enterprise from $599/mo.
Compare plansAlso comparing Chatbase?
If you are weighing a hosted chatbot trained on your content, see how Ethora compares with Chatbase.
Ethora vs ChatbaseAI agents running on Ethora today
Healthcare: HIPAA-compliant AI assistant (RAG) over a medical video library
Dr. Talks is one of the most prominent organizers of online healthcare conferences and summits.
Ethora enabled them to create a context-aware AI-powered chatbot to help users navigate thousands of pages of medical content, correctly referencing pages, authors, videos and timestamps. 100% secure and HIPAA-compliant.
This assistant enhances user experience by simplifying interaction with the platform and reducing search time.
- 1000+ summits indexed by AI bot
- Instant user engagement
- Vector embeddings enable intelligent domain expert AI responses
Communities: fan chat app with second-screen rooms and digital collectibles
A cross-platform social app uniting the automotive community around racing events.
Fan rooms for teams and drivers, second-screen events, and collectibles handed out and traded through chat bots.
- Cross-platform iOS and Android app
- Fan rooms and second-screen events
- Collectibles distributed in chat
Energy: dedicated chat server, AI-agent rooms and a React Native app for a procurement platform
Preshent is a US platform for energy-project procurement with AI-driven decision support.
Ethora provides the conversation layer: a chat room per project workspace shared by people and the AI agent, a dedicated chat server in Preshent’s own cloud, push notifications and a React Native app.
- 1,130 chat rooms, one per workspace
- AI agent as a participant in every room
- Dedicated chat server, 99.99%+ uptime
Professional services: a private, self-hosted AI assistant for a corporate intelligence firm
A London corporate intelligence and investigations firm whose analysts could not use public AI assistants on confidential client work.
Ethora designed a private AI assistant: a single-tenant server with AI agents, document search and an open-weight model on the firm’s own GPU, managed by Ethora in a London cloud region or installed on a workstation in the office.
- Local open-weight LLM, no public AI services
- Single-tenant server, UK hosting
- Cloud GPU or on-premise workstation
Virtual worlds: a 3D multiplayer world built from a book, with AI characters, in one weekend
An internal R&D showcase by Ethora’s founder: Alice in Wonderland, The Tempest and A Christmas Carol as 3D worlds you walk through in first person.
Each room is an Ethora chat, each character an Ethora AI agent with the book as its knowledge; a generator and the hosted MCP server build a new world from any book in about four minutes.
- Built in a weekend on the public SDK, API and MCP
- Characters answer in character from the text
- Daily AI budget keeps a public world affordable
AI agents on customer websites: support, intake and teaching assistants
Clinics, schools and small businesses build AI agents on Ethora themselves and put them on their own websites, often on the day they sign up.
3 examples, from a US mental health provider and a wellness brand to a university pharmacology course.
- WordPress plugin or one script tag
- Answers from the customer’s own pages and documents
- Self-serve, no developer needed
Migration
Moving from Botpress to Ethora
Your knowledge and your instructions carry over; visual flows do not import, because Ethora has no flow canvas. For most question-answering agents, the flow logic becomes instructions plus knowledge, and the rest becomes tool calls.
List what the agent knows
Collect the documents, web pages and tables behind your Botpress knowledge bases, and write down what each flow actually does.
Pick where Ethora runs
Sign up free on our cloud, or install the platform on your own servers with Docker Compose or Helm from Get Ethora.
Choose the model
Use a cloud model API, or point the agent at Ollama or vLLM. Our open example repository needs four environment variables, and RAG needs Postgres with pgvector.
Rebuild the agent
Create an AI agent, crawl your site and upload documents, then turn your flow logic into instructions and tools. You can also create and manage agents from Claude or another MCP client with the Ethora MCP server.
Embed it
Replace the webchat snippet with
<script src="https://widget.chat.ethora.com/assistant.js" data-app-id="YOUR_APP_ID"></script>before</body>, or add chat to your app with the web or mobile SDKs.Test with real questions
Run ten questions your users really asked in the Try it chat. It shows which sources each answer used, so gaps are easy to fix before you switch traffic.
Botpress alternative FAQ
Can I still self-host Botpress?
Botpress’s own documentation says v12 has been sunset and is no longer available for purchase, download or new deployments, and that this includes all other self-hosted or locally installed versions. New projects run on Botpress Cloud.
Can Ethora agents run on Ollama or vLLM?
Yes. Each agent can use a cloud model API such as OpenAI, or a model you host through an OpenAI-compatible endpoint such as Ollama or vLLM. In our open example a 3B model on a 4 vCPU, 8 GB CPU-only server answered short replies in 6 to 8 seconds.
Can I import my Botpress flows?
No. Ethora does not have a visual flow canvas, so flows are not imported. You bring over the knowledge and the instructions, and most question-answering logic becomes the agent’s instructions plus its knowledge base, with tool calls for actions.
Does Ethora support WhatsApp, Telegram or Messenger?
No. Ethora runs AI agents in a website widget and inside your own web and mobile apps through its chat SDKs. If those messaging channels are what you need, Botpress is the better fit.
Can I manage agents from Claude or other AI tools?
Yes. The Ethora MCP server (@ethora/mcp-server) lets Claude and other MCP clients create and manage your apps and AI agents.
Is there a free plan?
Yes. The free plan is $0 per month with 1,000 monthly active users and no credit card. Small Business is $149 per month and Enterprise starts at $599 per month.
Run AI agents on your own stack
Start on our free cloud plan, or self-host the open-source platform with the model you choose.
