
FutureSmart Agent
A complete AI Agent system for real use cases. RAG, NL2SQL, API actions, multi-agent logic — everything in one place.
Pulse AI - Autonomous AI Intelligence Agent
Individual
December 6, 2025 at 09:31 PM
hear-about-us
name
EVELYN EDJERE
College / University Name
Other
linkedIn-profile
Project Title
Pulse AI - Autonomous AI Intelligence Agent
Describe what your project does?
Share a 3–5 minute HD demo video
Hosted Project Link (if any)
GitHub Repository (if any)
artifacts/ supporting material
Is this project your original and proprietary work?
Yes
Does your project include any private, sensitive, or restricted code or content?
No
Do you give us (AI Demos & partners) permission to feature your work on our website and share it with our community (with full credit)?
Yes
Do you consent to us showcasing your name/profile on our social media platforms and YouTube
Yes
Are you open to freelance, internship, or collaborative opportunities based on this project?
Yes, I’m interested
Pulse AI is an autonomous AI intelligence agent built with LangGraph that revolutionizes how we consume AI/ML news. It scrapes multiple sources (ArXiv, GitHub, RSS feeds, blogs), uses embedding-based deduplication to surface novel content, generates LLM-powered summaries via Groq (Llama 3.3 70B), and auto-publishes to 2 platforms (Dev.to, Mastodon). The LangGraph StateGraph orchestrates a typed 6-node pipeline: scrape → dedupe → summarize → publish_devto → publish_mastodon → finalize. Each node handles a specific task with async execution and error accumulation. It even generates AI podcasts using Edge TTS (free!). Real-world problem solved: Information overload for AI researchers and enthusiasts. What takes hours of manual curation now happens automatically with intelligent filtering and multi-platform distribution.