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 Thumbnail

MDMA - GenUI for apps

Turn AI chat responses into interactive forms and workflows

Open Source
Developer Tools
Artificial Intelligence
GitHub
Visit WebsiteSee on Product HuntGithubTwitter

Hunted byMarcin SadowskiMarcin Sadowski

MDMA is an open-source format that lets LLMs respond with mounted applications — forms, approval gates, interactive tables, and webhook triggers — right inside Markdown. No custom UI needed. Works with any model: OpenAI, Anthropic, Gemini, or local.

Top comment

Hey Product Hunt! I'm Marcin, Co-founder and CTO at Mobile Reality, and I've been obsessed with one problem: AI chat responses are only text. LLMs can reason, plan, and write - but the moment they respond, everything collapses into a wall of plain text. Need user input? "Please fill in these fields." Need approval? "Reply YES to confirm." It's like having a genius assistant who can only communicate through sticky notes. MDMA (Markdown Document with Mounted Applications) changes that. It's an open-source format that lets any LLM respond with real, interactive UI: forms, approval gates, editable tables, charts and webhook triggers. All embedded right in Markdown. No custom frontend needed. No vendor lock-in. Works with OpenAI, Anthropic, Gemini, or your local model. Your AI response becomes an app. We've built the parser, the React renderer (but will add more renderers soon), a prompt pack for major LLMs, and an evaluation suite with 60+ tests. It's MIT-licensed and ready to use today. Would love to hear what use cases come to mind for you! What would you mount in your AI responses?

Comment highlights

Finally, interactive components instead of walls of text. MIT licensed and an MCP server included, going to try this on my next agent. Congrats on the launch.

We open-sourced MDMA because plain-text LLM output was the bottleneck in every agent we built. Now the model replies with forms, tables, approval gates and charts instead of paragraphs, parsed deterministically from Markdown plus YAML, with PII protection and an audit log built in. 98% reliability across GPT, Claude, Gemini and Llama, MIT licensed, MCP server and Agent Skill included. Try it and tell us what breaks, we read every issue.

About MDMA - GenUI for apps on Product Hunt

Turn AI chat responses into interactive forms and workflows

MDMA - GenUI for apps was submitted on Product Hunt and earned 9 upvotes and 5 comments, placing #46 on the daily leaderboard. MDMA is an open-source format that lets LLMs respond with mounted applications — forms, approval gates, interactive tables, and webhook triggers — right inside Markdown. No custom UI needed. Works with any model: OpenAI, Anthropic, Gemini, or local.

MDMA - GenUI for apps was featured in Open Source (68.5k followers), Developer Tools (514k followers), Artificial Intelligence (471k followers) and GitHub (41.3k followers) on Product Hunt. Together, these topics include over 207.4k products, making this a competitive space to launch in.

Who hunted MDMA - GenUI for apps?

MDMA - GenUI for apps was hunted by Marcin Sadowski. 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.

Want to see how MDMA - GenUI for apps stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.