Join Vultr Community

Points, levels & badges

Enter challenges & submit builds

Register to events & meetups

Get your work featured

DISCLAIMER - Because I did this on a mac mini, the native video demo was not successful - please watch demo video here - https://live.trusynth.com/record Every promise you make out loud, kept. You meet someone, then text Chief one line: who they were and what you promised. Chief opens a Band room. Synths work in their own live browsers. Scout runs on its own Vultr computer and reads real pages. Echo drafts the follow-up. Chief, the critic, BLOCKS any claim nobody said. A second Synth checks…

View project

Buttery is an agent-first household food ledger. You manage your food by talking to the AI assistant you already use (Claude, ChatGPT/Codex, any MCP client): share a Costco receipt, a fridge photo or a recipe screenshot, or just say "I froze the chicken". Buttery keeps a trustworthy record of what food the household has, the evidence behind each belief, and what is about to expire. A small mobile web app handles quick reviews and corrections through links the assistant hands you. It is honest…

View project

Dreamnetiopi is an AI ops team for shops that sell at events and online. The owner already has a store, a scheduler, and AI copy. They are still the glue. Hack Day demo — Coastal Freeze Co at Pier 48: “We’re out of strawberries. Push mango and blue raspberry.” A Band room splits the work with @mentions. OpenRouter rewrites the offer and a short post. Nothing goes live until the owner approves. The room log is the receipt. Pre-pilot. No customers or revenue claimed.

View project

Kettle is a flock of AI agents — Sales, Procurement, Finance — that run a mid-size company's back office together on Vultr, sharing one auditable ledger and stopping for human sign-off on anything that spends money.

View project

One Slack channel for events, office snacks, swag, and budgets—coordinated by four agents with shared memory on Vultr.

View project

RAID — Report Agent for Intelligent Decisions Enterprise AI that investigates before it decides. RAID helps enterprises make high-stakes decisions by investigating their documents and data before providing a recommendation. Instead of generating a single AI answer, RAID performs a structured investigation: it gathers evidence, analyzes information, verifies findings, and produces a clear report explaining how the decision was made. Problem: Every day, organizations make decisions worth…

View project

VisionOps is a multimodal AI strategist that hears your business challenge, sees your whiteboard, and draws live strategic frameworks SWOT, competitive maps, business model canvases while speaking its analysis in real time. No typing. No switching tools.

View project

Themis turns a 3-minute closed-option chat into a typed, costed, carbon-rated AI adoption plan. Recommendations span Google, Anthropic and OpenAI. Every plan ships with monthly EUR cost and an EU-style A–E carbon rating — no AI expertise required.

View project

Upload any meeting recording. RELAY transcribes with Speechmatics speaker diarization, labels each voice to a real person, then Gemini 2.5 Flash drafts a complete enterprise proposal in one API call. Teams collaborate live. Every edit is logged.

View project

Executor is an autonomous meeting-to-execution agent that extracts commitments, syncs them to Jira, Asana, and Notion, monitors deadlines, and drafts follow-ups or manager escalations when execution stalls.

View project

Dasalt 360 is a high volume IT company, which buy laptops from USA and sell it from Jimeta, Adamawa State to another place. I built a multi-modal AI Agent to help procurement planning, logistics, sells and operational challenges.

View project

A voice-first thinking canvas. Talk through a decision, plan, or problem; what you say becomes typed cards you can refine by voice or chat.

View project