tokens&
BrowseFor enterprises
tokens&

Find tools, check provider offers, save a build plan, and share your work when you’re ready.

For buildersFor enterprises

For builders

  • Product launches
  • Builder projects
  • Startup credits and perks
  • Agent Skills
  • Published agents
  • API and agent docs
  • Publish a project

For enterprises

  • Start free company workspace
  • Submit a tool, product, or perk

Community

  • Community
  • Newsletter
  • Events
Xin

© 2026 tokensand, LLC. All rights reserved.

  • Terms
  • Privacy
  • Security
  • Data Processing
  • Status
  1. Hackathon
  2. Project gallery
  3. StreetCast
Muskan Dhingraabout 1 month agoContributorJudging locked: Event build

StreetCast

StreetCast turns New York street video into cited, ready-to-file 311 reports. A rider's footage becomes every blocked bike lane, trash pile and obstruction, with the clip and the truck's fleet number, never a plate. A newsroom picks a block and gets a narrated segment where every line cites a clip.

Community votes recognize the build and do not affect official judging.

Review the project

Start with the source code, then open the demo or video if available.

View GitHub repository
Watch demo videoProject gallery
Demo video
Watch demo video
Project description
StreetCast turns hours of street video into a cited record of what's blocking New York's streets, and helps people act on it. For riders (Ride report): a delivery cyclist records her ride. StreetCast replays it and every problem lands as a field note: blocked bike lanes, double parking, trash, obstructions, graffiti, construction. Each one comes with a drafted 311 complaint: category, street, what happened, the company and fleet number, and a link to the exact clip. It also shows how much time she lost and what caused it. Fleet numbers, never license plates: accountability for companies, privacy for people. For newsrooms (Your Block): a producer picks a neighborhood, a time of day and a travel mode. StreetCast runs six searches across the footage and builds a one-minute narrated segment. Every sentence cites the clip and time range it came from. No clip, no sentence. Eval: claims are checked against the clips they cite, and we report the grounding rate. How it works: VAST stores, indexes and searches the footage in VastDB. NVIDIA Cosmos Reason describes every clip, Cosmos Embed powers the search, and YOLO11 detects objects. An LLM on W&B Inference turns those descriptions into structured events and scripts, with every call traced in Weave. Built with Cursor. Rider files it. The city sees it. The newsroom airs it.
Project links
  • GitHub repository
  • Demo video
Tools used
  • VAST Data logoVAST Data

    Provider website

    Sign in to visit
Builder

Muskan Dhingra

Builder on tokens&

  • SpaceXAI (Cursor) logoSpaceXAI (Cursor)

    Event resource · Sign up for Cursor

    Sign in to visit
  • CoreWeave (Weights & Biases) logoCoreWeave (Weights & Biases)

    Event resource · Create a Weights & Biases account

    Sign in to visit
  • NVIDIA logoNVIDIA

    Provider website

    Sign in to visit