This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Chatvia.ai
Ditch every AI agent subscription. Open source, self-hosted
First public release. Install Chatvia on your own server with one command and get AI agents that answer from your documents and websites with sources, call your tools and any MCP server, and work on your site, in Slack, WhatsApp, Teams or Telegram. Bring any model, including open-weight ones with vLLM or Ollama. Free with no limits on agents, teams or replies. The full source is on GitHub.
Every AI agent tool I tried was a subscription that wanted my company's documents on someone else's servers, charged per seat or per message, and tied me to one model. I wanted the opposite: something I could install on my own server, read every line of, and point at any model I like. So I built it.
What it does
You install Chatvia with one command, upload your documents or import a website, and you have an agent that answers from them, with sources. Then you connect it to your tools (your own HTTP endpoints or any MCP server; risky calls wait for a person to approve) and put it where people already talk: your website, Slack, WhatsApp, Teams, Telegram, or through an API.
Hybrid search (vector + BM25) inside PostgreSQL, so there is no separate vector database to run
Any model: OpenRouter, OpenAI, Gemini, Mistral, Groq, or open-weight models on your own hardware with vLLM or Ollama
Guardrails, evaluations scored by an LLM judge, chat logs with sources, and handoff to a human
Workspaces, roles, audit logs, passkeys and IP allowlists for teams that need them
And much more ...
It is free to run with no limits on agents, teams or replies, and the full source is on GitHub.
A license key only hides the "Powered by Chatvia" credit and adds extras like the API and voice.
What feedback would help most
If you run support or an internal help desk: what would stop you from self-hosting this instead of paying for Intercom, Chatbase or a ChatGPT seat?
If you are a developer: try the install (https://chatvia.ai/docs) and tell me where it was unclear or broke.
Which channel or integration is missing for you?
I will be here all day answering questions. Thank you for looking.
About Chatvia.ai on Product Hunt
“Ditch every AI agent subscription. Open source, self-hosted”
Chatvia.ai was submitted on Product Hunt and earned 3 upvotes and 1 comments, placing #106 on the daily leaderboard. First public release. Install Chatvia on your own server with one command and get AI agents that answer from your documents and websites with sources, call your tools and any MCP server, and work on your site, in Slack, WhatsApp, Teams or Telegram. Bring any model, including open-weight ones with vLLM or Ollama. Free with no limits on agents, teams or replies. The full source is on GitHub.
On the analytics side, Chatvia.ai competes within Open Source, Developer Tools and Artificial Intelligence — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Chatvia.ai performed against the three products that launched closest to it on the same day.
Who hunted Chatvia.ai?
Chatvia.ai was hunted by Ahmad Mayahi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Chatvia.ai including community comment highlights and product details, visit the product overview.
Ahmad Mayahi
Hi Product Hunt 👋
I'm Ahmad, and I built Chatvia.ai.
Why I built it
Every AI agent tool I tried was a subscription that wanted my company's documents on someone else's servers, charged per seat or per message, and tied me to one model. I wanted the opposite: something I could install on my own server, read every line of, and point at any model I like. So I built it.
What it does
You install Chatvia with one command, upload your documents or import a website, and you have an agent that answers from them, with sources. Then you connect it to your tools (your own HTTP endpoints or any MCP server; risky calls wait for a person to approve) and put it where people already talk: your website, Slack, WhatsApp, Teams, Telegram, or through an API.
Hybrid search (vector + BM25) inside PostgreSQL, so there is no separate vector database to run
Any model: OpenRouter, OpenAI, Gemini, Mistral, Groq, or open-weight models on your own hardware with vLLM or Ollama
Guardrails, evaluations scored by an LLM judge, chat logs with sources, and handoff to a human
Workspaces, roles, audit logs, passkeys and IP allowlists for teams that need them
And much more ...
It is free to run with no limits on agents, teams or replies, and the full source is on GitHub.
A license key only hides the "Powered by Chatvia" credit and adds extras like the API and voice.
What feedback would help most
If you run support or an internal help desk: what would stop you from self-hosting this instead of paying for Intercom, Chatbase or a ChatGPT seat?
If you are a developer: try the install (https://chatvia.ai/docs) and tell me where it was unclear or broke.
Which channel or integration is missing for you?
I will be here all day answering questions. Thank you for looking.