Amit.dev
The whole story

The AI Engineering Toolkit

Eleven pieces that fit together: design a workflow, run it, evaluate the AI in it, review the code around it, ship it, then integrate or embed it anywhere. Every tool below is either open-source, live on this site, or a real shipped product — no slideware.

The end-to-end flow
flowchart LR
  A["Design<br/>(Workflow Builder)"] --> B["Run"]
  B --> C["Evaluate<br/>(ai-eval)"]
  C --> D{"Pass?"}
  D -- "yes" --> E["Ship"]
  D -- "no" --> A
  E --> F["Review on PR<br/>(PR Reviewer)"]
  E --> G["Integrate via MCP<br/>(Inspector + servers)"]
  E --> H["Embed on any site<br/>(SiteAsk)"]
  classDef tool fill:#eef2ff,stroke:#6366f1,color:#3730a3,stroke-width:1px
  classDef io fill:#fef3c7,stroke:#d97706,color:#7c2d12,stroke-width:1px
  class A,C,F,G,H tool
  class B,E io

Design & Run

Compose chained LLM steps into a workflow you can actually run.

live tool

AI Workflow Builder

Chain LLM, fetch, and assert steps. Outputs flow via {{stepId.output}}. Streams live with per-step latency.

Evaluate

Test the AI itself — catch prompt regressions before users do.

OSS

ai-eval

Open-source CLI + GitHub Action + web viewer. YAML test cases with contains / regex / equals / llm-judge assertions. Non-zero exit on failure for CI.

Review

Multi-agent code review running on real public PRs.

live tool

Multi-Agent PR Reviewer

Paste any public PR URL. Four specialised agents (correctness · security · style · tests) review in parallel; a lead reviewer synthesises a structured verdict.

live tool

AI Commit Message Generator

Paste a git diff, get a Conventional Commits message with the right type/scope and a body that explains the WHY.

Connect & integrate

A complete Model Context Protocol toolkit — visualise the wire, run a reference server, scaffold new ones, and generate them from any OpenAPI spec.

MCP Inspector

Inspectable JSON-RPC trace of a typical MCP session — initialize, capability discovery, tools/list, tools/call.

OSS

portfolio-mcp

The real working MCP server that exposes Amit's blog to Claude Desktop, Cursor, Cline.

OSS

create-mcp-server

Interactive scaffolder. `npm create mcp-server@latest` → working MCP server with a Claude Desktop config snippet in 30 seconds.

live tool

API → MCP Generator

Paste an OpenAPI 3.x spec — an LLM streams a complete TypeScript MCP server that exposes each endpoint as an MCP tool.

Embed in any site

A drop-in AI chat widget anyone can install with one script tag.

OSS

SiteAsk

Browser-side RAG, BYOK LLM, source-citable answers. No vector DB, no per-chat SaaS fees. One <script> tag.

Explore patterns

Fifteen browser-runnable AI demos that illustrate the underlying patterns — embeddings, retrieval, agents, tracing, memory, reasoning, tokenisation.

demos

AI Labs

Gallery of 15 interactive demos: Multi-Agent Orchestrator · Tool-Use Simulator · Agent Memory · Reasoning Visualizer · RAG Playground · Hallucination Detector · …

Ask Amit assistant

Floating chat (bottom-right of every page) — browser-side embedding, sourced answers from the portfolio's RAG index.

Real shipped products

AI products living outside the portfolio.

commercial

JobJam.io

Commercial AI-native job search and application platform. Next.js + Anthropic Claude + Supabase + Stripe. One-time pricing, no subscriptions.

edge

NanoClaw (Raspberry Pi)

AI agent running on a $35 Raspberry Pi 3, scanning receipts and tracking spending via Discord for ~$1/month.

This portfolio (AI-native)

Chat assistant + ⌘K semantic search + 15 demos, all sharing one browser-side embedding model and a single retrieval index.

Try the whole thing in one minute

Open a workflow → watch it run → click into ai-eval to see how the same prompts get tested → click the chat icon in the bottom-right of any page to see SiteAsk in action — that's the toolkit.

Start at Workflow BuilderRead the source