More Flutter and Dart and AI, Oh My!
summary
A usable Flutter AI chat widget (Flutter AI toolkit v0.9.x) ships with Firebase provider support to hide API keys, pluggable LLMs (Gemini, OpenAI, Anthropic, Llama.cpp, etc.), persistent chat history, styling and multimedia, and live tool calls including multi-step calls to MCP servers (demonstrated against Zapier calendar data). A separate agent framework, Dartantic, runs identical agent code across Flutter, CLI (Chatarang) and Serverpod, claims support for 341 models, and successfully handles embeddings, RAG and multi-provider agent switching.
AI-written summary · about
chapters (14)
- 0:00Introduction
- 2:36Flutter AI toolkit overview
- 5:33Live demo of Flutter AI toolkit
- 9:51Tool calls and MCP
- 12:19Model Context Protocol deep dive
- 22:47Introducing Dartantic AI
- 26:22Cross-platform AI with Dartantic
- 32:09Chatarang CLI and chat
- 33:13Dartantic server and Flutter
- 35:47Why Dartantic and future
- 36:09AI for productivity
- 37:34Coding vs vibe coding
- 41:10Future of Flutter AI toolkit
- 42:14Closing
related talks
42mDart and Flutter and AI, Oh My!
01h 11mBuild Your Own AI Sidekick with Flutter
14mPrompt to production: Building an AI app with Flutter
01h 19mFull Stack AI Features
32mFrom Flutter to Full-Stack
42mKeynote - Let's go far with Flutter
16m5 most useful AI skills that I use with Flutter everyday
49mWhat's Awesome about Flutter
