FrootAI — AmpliFAI your AI Ecosystem Get Started

FAI VS Code Extension

Browse, search, and build — right from your editor

Install from VS Code Marketplace

Open VS Code → Extensions (Ctrl+Shift+X) → Search "FrootAI" → Install

Or from terminal: code --install-extension frootai.frootai-vscode

Open on VS Code Marketplace →

What You Get

Solution Plays
Browse all plays in the sidebar. Click to open README or folder.
FROOT Modules
Knowledge modules grouped by layer. Click to open and read.
MCP Tools
See all MCP tools at a glance. Know what your agent can do.

Commands (Ctrl+Shift+P)

FrootAI: Initialize DevKitFull .github Agentic OS (19 files) + agent.md + MCP + plugin.json
FrootAI: Initialize TuneKitconfig/*.json + infra/main.bicep + evaluation/ — AI tuning for production
FrootAI: Install MCP ServerInstall globally, run via npx, or add .vscode/mcp.json config
FrootAI: Start MCP ServerLaunch frootai-mcp in terminal (tools: engine, scaffold, marketplace + classic)
FrootAI: Initialize HooksCopy guardrails.json (preToolUse policy gates) to your project
FrootAI: Initialize PromptsCopy 4 slash commands (/deploy, /test, /review, /evaluate)
FrootAI: Look Up AI TermComprehensive glossary — inline popup with rich definition
FrootAI: Search Knowledge BaseFull-text search across bundled knowledge modules
FrootAI: Open Solution PlayView play in rich webview panel (standalone)
FrootAI: Show Architecture Pattern7 decision guides: RAG, agents, hosting, cost
FrootAI: Open Setup GuideOpens the setup guide on the website
FrootAI: Browse Solution PlaysOpens the solution plays page

How DevKit Init Works (v2)

1. Run Ctrl+Shift+P → FrootAI: Initialize DevKit

2. Select a solution play (e.g., Enterprise RAG)

3. FrootAI copies the full .github Agentic OS to your workspace:

4. Start coding — Copilot generates solution-aware code with full agentic OS context.

  • Layer 1: instructions/*.instructions.md — coding standards, patterns, security
  • Layer 2: prompts/*.prompt.md — /deploy, /test, /review, /evaluate
  • Layer 2: agents/*.agent.md — builder → reviewer → tuner (chained)
  • Layer 2: skills/*/SKILL.md — deploy-azure, evaluate, tune
  • Layer 3: hooks/guardrails.json — preToolUse policy gates
  • Layer 3: workflows/*.md — AI-driven CI/CD
  • Layer 4: plugin.json — distribution manifest
  • + agent.md + .vscode/mcp.json — co-coder + MCP