{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/8909d82ccb88495688692f2cb05f90fe\" frameborder=\"0\" width=\"3840\" height=\"2880\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":2880,"width":3840,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":2880,"thumbnail_width":3840,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/8909d82ccb88495688692f2cb05f90fe-167514e30b798629.gif","duration":79.966667,"title":"Build Real Time Chat With Fluxychat","description":"HI, I'm Alessandro. \nI built Fluxychat over the past 2 months because I wanted a small, inspectable realtime chat stack on Cloudflare (Workers + Durable Objects + D1) instead of running a separate socket fleet and a heavy SaaS bill for “just rooms + delivery + ops hooks.”\n \nWhat it is:\nFluxyChat is a hosted multi-tenant chat backend (REST + WebSocket) with a Next.js operator console and a JavaScript SDK. A room is a channel; JWTs are scoped by tenant/project; the Worker holds room state in Durable Objects.\n \nLive URLs:\n- Try / sign up: https://www.fluxychat.com/get-started  (→ onboarding → console)\n- Console (after auth): https://www.fluxychat.com/rooms and https://www.fluxychat.com/agents\n- API: https://api.fluxychat.com\n- Overview + demo video: https://www.fluxychat.com/landing\n- In-app docs: https://www.fluxychat.com/docs\n \nHow to try it today (beta, account required):\n1. Open https://www.fluxychat.com/get-started and create an account (Clerk — email verification may apply).\n2. Complete the onboarding wizard (creates a project and shows your API key flow).\n3. Open Rooms — create or join a room, send messages over WebSocket.\n4. Open Agents — configure an agent (your LLM provider keys go to the Worker/console, not the npm package), open the agent room chat, @mention the agent or invoke from the UI.\n \nThere is no anonymous guest room yet; signup is the friction I’d like feedback on.\n \nWhat’s in this open beta (shipping in prod now):\n- Worker on Cloudflare: rooms, messages, presence-style realtime over WebSockets, webhooks, quotas in D1.\n- Dashboard: projects, rooms, search, agent profiles, LLM provider registry + credentials.\n- Agents: tool calls and tool results streamed in the thread; run status (latency/tokens/errors) on the wire; reply-to via parent_id; optional history replay modes in the SDK (connect vs explicit request).\n- Operator UX: prompt templates picker, assistant room entry from /rooms, LLM fallback provider in agent config.\n- SDK: @fluxy-chat/sdk — FluxyChatClient, useChat, FluxyRealtimeProvider; cookbook for bot streaming: (add your public doc URL if published, e.g. GitHub docs path)\n \nWhat I am NOT claiming / not in this beta:\n- Not a hosted MCP server or OpenCode-style TUI clone.\n- No separate “sessions” API — we use rooms as channels by design.\n- Threads/polls/machine translation are left to your product layer; Fluxychat ships the realtime core.\n \nArchitecture (factual):\n- Browser → Next.js dashboard (Vercel, www.fluxychat.com).\n- Browser & your backends → Worker API (api.fluxychat.com): HTTP + WebSocket.\n- Hot path: one Durable Object per room for coordination/delivery (details in repo/docs).\n- LLM keys: configured per project/agent on the Worker side; the SDK only carries your Fluxy member JWT / project API key for auth.\n \nBackstory / why it might be interesting:\nI kept scope narrow on purpose: multi-tenant chat with clear quotas, middleware hooks, and a console for day-two ops — without bundling a full “AI IDE.” The current push is making agent runs observable in the same room timeline (tools + run metadata) so you can debug automations like you debug chat.\n \nRepo:\n- GitHub URL: https://github.com/AlessandroFare/fluxychat\n \nI’d especially like feedback on:\n1. Whether the signup/onboarding path is acceptable or if I should prioritize a no-login demo room.\n2. SDK DX (useChat, replay modes, error surfaces on agent runs).\n3. Pricing/quotas model for a Worker-native chat SaaS — what would make you try vs self-host?\n \nThanks for poking at it — happy to answer technical questions on DO layout, auth, and agent invoke paths."}