Overview
nuncio is an autonomous agentic pipeline that turns any public social profile into a personalised, fully rendered video — with zero human intervention between input and output.
Paste a LinkedIn, Twitter/X, or GitHub URL. The agent enriches the profile in parallel via TinyFish, synthesises a detailed recipient profile with personalisation hooks, then writes a tailored 60-second script using Claude (with Featherless Qwen3/DeepSeek fallbacks). A creative agent generates supporting visuals via Melius MCP (or Fal FLUX), while HeyGen’s Video Agent renders the final video using a cloned voice and avatar. Speechmatics automatically generates timed captions.
Every agent decision is surfaced in the UI — including which sources were used, which details were referenced, and what was intentionally skipped. The output is a branded share page (/v/[id]) with a built-in “Make your own” CTA.
Built with Next.js 16 and deployed on Vultr via Coolify. Uses TinyFish (enrichment), Featherless + Anthropic (reasoning), Speechmatics (captions), Melius (creative canvas), HeyGen (video rendering), and Turso (share records). Open source under MIT. Live demo: nuncio.persidian.com.
Note: the demo URL is substituted with the GitHub repository link.
Tech stack
No comments yet
Be the first to comment on this project.
sentinel
Full-Stack Self-Healing DevOps & Security Copilot The Concept: An AI operations engineer that doesn't just suggest code fixes—it monitors cloud infra, detects uptime/security drops, automatically provisions fixes, and generates audit reports for enterprise compliance.
Agency Compiler
Agentic creative project compiler. Most creatives, agencies and designers dont know how to use ai, none the less agents. We created a platform that allows a creative agency or studio owner to instantly spin up agents based on the project ask, resources and scale.
ProofRun
ProofRun helps developers answer a critical question before shipping: will this update break behavior users rely on? An AI agent inspects two Git revisions, designs targeted experiments, and proposes repairs. An independent Docker-based verifier runs those experiments against both versions, preserves the original tests, and checks whether the repair actually works. Developers receive an update, skip, or postpone recommendation with recorded evidence and a reviewable patch. In a live synthetic…