
Overview
Win more deals customer and VC deals. Stop guessing why you lost. RevAgent is three AI agents that fix the parts of selling that kill early-stage founders: weak pitch decks, rambling discovery calls, and lost deals you never debrief. Drop in a deck or a transcript, get back specifics you can ship today. The three agents Agent Trigger Powered by Output Pitch Surgeon Upload .pptx / .pdf deck Gemini 3 Pro (multimodal) 3 scores · weakest-slide rewrite · 30-sec narrated pitch Discovery Co-Pilot Start a live call from the browser Speechmatics RT (diarized) + Gemini Flash Live JTBD switch chart · mid-call nudges · 3 follow-ups Win-Loss Auditor Drop transcript + outcome label Featherless (4 specialized OSS models) PDF digest emailed via Resend — objections, patterns, classification, verbatim language Each agent uses what the sponsor stack is actually best at. No costume integrations.
Note: the demo URL is substituted with the GitHub repository link.
No comments yet
Be the first to comment on this project.

StylePilot AI – AI-Powered Pre-Meeting Research Agent
An AI-powered research agent that gathers information from multiple sources and generates structured, actionable pre-meeting briefings.

HackGlobal 2026 - Super Secure Syst v23 - 6 Detect Multispektrum + Bio Healthy Room
6-in-1 multispectral agent for Food, Room, Derma, Naphtol, Forensic and Gem check. IMX219 + MLX90640 Thermal + NDIR 4-channel on Vultr, with Bio Healthy Room monitoring and certificate printing.

Tally: an airlock for supplier invoices
Tally opens every supplier invoice in a throwaway Microsandbox microVM on a Vultr VX1, reads only its page images with two model families on Vultr Serverless Inference, and lets fixed rules, not a model, decide what is held. A voice desk device announces each hold.


