Launching today

Multi-Agent Content Engine

Launching today

Turn topics into X, LinkedIn & Insta campaigns via AI agents

6 followers

Turn topics into X, LinkedIn & Insta campaigns via AI agents

6 followers

•

•

Stop wasting hours writing social copy. The Multi-Agent Content Engine uses CrewAI & Gemini 3.1 Flash-Lite to orchestrate a sequential workspace of specialized agents: 🕵️‍♂️ Researcher: Extracts core insights & buyer personas. ✍️ Copywriter: Structures X threads, LinkedIn posts, & IG captions. 🧼 Editor: Polishes sentence flow. This is an open-source, Bring-Your-Own-Key storefront built with Streamlit. Paste your Gemini API key in the sidebar to run full campaigns for free!

Multi-Agent Content Engine gallery image

Free

Launch tags:Social Media•Marketing•Artificial Intelligence

Launch Team / Built With

Framer AI AgentsDesign and publish professional sites with AI

Promoted

Maker

📌

Hey Product Hunt community! 👋 I’m Mohith, the creator of the Multi-Agent Content Engine. I built this tool because I was frustrated with standard LLM prompts when trying to draft marketing content. Traditional single-prompt architectures often mix up context, produce bloated text, or fail to capture the unique nuances of different social platforms. To solve this, I built a sequential multi-agent assembly line using CrewAI and Google’s Gemini 3.1 Flash-Lite. Instead of one prompt doing everything, the workload is broken down into specialized roles: 1️⃣ A Lead Researcher who extracts core insights and analyzes target audiences. 2️⃣ A Social Media Copywriter who translates those insights into native platform layouts (X threads, structured LinkedIn posts, and Instagram descriptions). 3️⃣ A Chief Brand Editor who audits line breaks, formatting, and scannability. To keep it 100% open-source and free for the community, I designed the storefront layout using Streamlit with a Bring-Your-Own-Key (BYOK) system. Your API key stays securely inside your browser's session state memory, running entirely on your own quota with $0 cloud markup. I’ve also optimized the backend with an automated headless browser pipeline using GitHub Actions to ensure the hosting container stays hot and never hits a hibernation wall when you need it! I would love to get your honest feedback: 1. How do you feel about the output quality compared to standard ChatGPT or Claude prompts? 2. Are there any specific marketing platforms or custom brand-voice features you'd like to see added next? The code is fully open-source, so feel free to fork the repository, play with the agent parameters, or drop a star! Thank you so much for the support! 🚀

Report

17h ago

the sequential handoff between the researcher, copywriter, and editor agents is genuinely clever, it actually feels like a tiny production line rather than just one model doing everything. love that it is open source too, easy to tinker with.

Report

7h ago

honestly this looks pretty cool, the multi-agent setup is a neat approach. one thing that would help a lot is adding a memory or style profile per brand, so the copywriter agent doesn't reset to generic voice every time you start a new session. basically let users save their tone guidelines, key phrases, and past examples, then the agents reference that before generating. would make repeat runs way more consistent.

Report

6h ago

Really like how clean the agent handoff is in the flow, basically each step knows exactly when to hand off to the next instead of dumping everything into one prompt. Also the BYOK setup in the sidebar is a nice touch for anyone who actually wants to tinker without paying for yet another subscription.

Report

1h ago