Loading repository data…
kevinkamto / repository
A full-stack AI research agent that breaks complex questions into parallel research threads, searches the web, summarizes findings, and synthesizes a final report - all streamed live to the UI.
A full-stack AI research agent that breaks complex questions into parallel research threads, searches the web, summarizes findings, and synthesizes a final report - all streamed live to the UI.
Running - parallel researcher threads searching the web, results streaming in real time
Complete - synthesized markdown report with all sources
frontend (Next.js 16) ←→ backend (FastAPI + LangGraph)
↓
START → planner → [Send ×N] → researcher (parallel)
↓ (merge)
summarizer
↓
synthesizer → END
| Directory | Stack |
|---|---|
frontend/ | Next.js 16 + React 19 + TypeScript + Tailwind CSS v4 |
backend/ | FastAPI + LangGraph + langchain-openai + Tavily |
cd backend
uv sync
cp .env.example .env # fill in OPENAI_API_KEY, TAVILY_API_KEY
uv run main.py
cd frontend
pnpm install
cp .env.example .env.local # set NEXT_PUBLIC_API_URL
pnpm dev
App runs at http://localhost:3000, backend at http://localhost:8000.
backend/.env)OPENAI_API_KEY=sk-...
GROQ_API_KEY=gsk_... # optional, for Groq provider
TAVILY_API_KEY=tvly-...
LLM_PROVIDER=openai
LLM_MODEL=gpt-4o-mini
frontend/.env.local)NEXT_PUBLIC_API_URL=http://localhost:8000
Selected from shared topics, language and repository description—not editorial ratings.
gareev-bulat /
A full-stack co-op application tracking platform for Drexel students, extended with a multi-agent AI pipeline (CrewAI + Claude API) that autonomously discovers, scores, and tailors postings. Kanban pipeline, analytics dashboard, Supabase PostgreSQL backend. Built with Next.js 16, TypeScript, and Tailwind CSS.
engrmumtazali0112 /
Full-stack technical assessment submission: a Flask REST API with a 3-agent AI pipeline (`backend/`) and a React/TypeScript dashboard that consumes it (`frontend/`).
AsifAhmedSahil /
Nexa is an intelligent agentic AI system that transforms natural language prompts into fully functional full-stack applications. It enables users to describe what they want to build, and the system automatically generates structured backend logic, frontend UI, and integrated workflows using modern AI orchestration techniques.
AralAutomata /
Full Stack Agentic AI Pipeline for Educational Use: Deno runs the LangChain/LLM agent backend + Bun runs the Next.js UI + SQLite database for audit and history + Per-entity memory and immutable snapshots logged as JSON provide continuity across run cycles + TypeScript Fun Time