Project Info

CollabAI

Devpost

This project did not submit a demo video on Devpost.

Inspiration

Every team has been there — the confusion of group projects, whether at school, at a startup, or during a hackathon. People make promises in chats, share files, throw ideas around — and somewhere along the way, clarity gets lost. We drew inspiration from tools like Slack, which succeeded not by adding another chat app, but by rethinking how teams communicate effectively.

What it does

CollabAI is doing the same for project coordination. Instead of yet another tool where chaos unfolds, CollabAI brings clarity — by combining workspaces, group collaboration, and AI that actually listens and remembers. ✅ Workspaces for real collaboration — Users can create workspaces, form groups, and invite friends or colleagues to work together on projects. ✅ AI memory of everything — Our AI listens to all chats, tracks tasks, and reads every document or file your team shares. It builds a shared memory of your project’s commitments, discussions, and deadlines. ✅ Context-aware AI assistant — The AI doesn’t just respond to prompts. It proactively tracks progress, identifies risks, sends reminders, and ensures your team stays on course. 👉 The crux: CollabAI is not just a chat app with AI — it’s an AI that understands and remembers your entire project context so no commitment, task, or deadline is forgotten.

How we built it

We built CollabAI using: Next.js + Tailwind CSS → For a modern, clean, and responsive frontend with server-side rendering for speed and SEO. Supabase → To handle authentication, real-time database storage, and secure management of workspaces, chats, files, and AI-extracted tasks. Claude 4 API → To parse chat conversations and extract tasks, deadlines, owners, and generate context-aware summaries and reminders. Unify Multimodal AI API → To process uploaded files, images, screenshots, PDFs — enabling the AI to reason across both textual and visual inputs. Multi-agent AI architecture → Built to modularize CollabAI’s reasoning: Parser Agent → Extracts tasks, deadlines, owners from chat + files Tracker Agent → Monitors task progress against commitments Notifier Agent → Sends reminders, deadline nudges Analytics Agent → Predicts deadline risks and highlights overlaps

Challenges we ran into

Real-time memory and storage: Ensuring Supabase handled evolving chat + file + task data efficiently without lag in AI updates. UX of AI outputs: Making sure our AI-generated summaries, task lists, and reminders were clear, actionable, and added value without noise.

What we learned

A good idea matters first, execution follows !!

Analysis

Compare with all teams

No indexed repository for this project, so there are no commit stats to show.

Technology

Found in codeNot checked
  • Google GeminiUnchecked
  • Next.jsUnchecked
  • SupabaseUnchecked

No repository was indexed for this project, so these Devpost claims have not been checked against code.

AI coding agents

No repository was indexed, so agent usage could not be checked.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

No repository was indexed, so there is no codebase to measure.

0 stars