Projects using OllamaProjects using Ollama
Projects
People
Cover image for Not every OnSense user is
Not every OnSense user is on the mobile app — some just want to ask a quick question about their appliance from a browser. Appliance GPT was built as a standalone web product: a focused, consumer-facing chat interface where anyone can describe an issue or ask about error codes, parts, or repairs and get an answer trained on appliance-specific knowledge, without needing to install anything. What I built I built the chat UI solo, using React and Next.js — the conversational interface, message flow, and front-end experience that consumers interact with directly at appliancegpt.onsense.ai (http://appliancegpt.onsense.ai). Stack: Next.js and React for the web chat interface Integration with OnSense's underlying AI/repair-knowledge backend What shipped A live, standalone web app giving consumers direct access to an AI appliance-support assistant — no app download required, just open the browser and ask.
0
39
Cover image for It all started on a
It all started on a Sunday at the AWS User Group Mumbai meetup. I wasn't expecting to walk away with a new obsession, but then the speaker introduced me to Temporal and everything changed. Temporal is a durable execution engine that solves one of the hardest problems in agentic AI what happens when your LLM workflow crashes mid-run? Normally you lose everything So I went home and built this: an agent that monitors your competitors around the clock tracking pricing changes, product launches, hiring signals, and strategic moves. Every 24 hours it uses Mistral (running fully on-device via Ollama) to analyze the data and synthesize a structured executive briefing delivered straight to your inbox. Sometimes the best projects start with a Sunday conversation. https://github.com/AnuragNagare/Agentic-AI-.git
0
77
Cover image for Introducing TokenPulse AI - paste
Introducing TokenPulse AI - paste a token address, get a scroll-stopping video in one click. 🎬📈 Crypto moves fast, and the content can't keep up. TokenPulse AI fixes that: drop in any Solana token address and it analyzes the market, detects the pump, and auto-generates a vertical, trading-terminal-style video plus a ready-to-post caption -: the kind of content that stops the scroll. Built as a modular, multi-agent system: 🔍 Live market data (DexScreener + GeckoTerminal) 🤖 Multi-agent pipeline - research → signal → narrative → QA → copy - running on a local LLM 🎬 Remotion-rendered 1080×1920 video with a beat-synced audio drop on the pump 🔥 Auto-discovery feed of trending tokens - one-click generate 🛡️ Compliance + safety scoring baked in (no financial advice, clear disclaimers) ✅ Human-in-the-loop approval before anything ships Stack: TypeScript monorepo (Turborepo) · Next.js · Fastify · BullMQ · Postgres/Prisma · Remotion · Ollama · Docker.
0
76