Ethereum dApps, one curl command away

How it works

Your code never leaves your machine

No cloud API keys, no usage billing. Terminal → Ollama → dApp review report — that's the whole pipeline.

1. 01

   Send the source

   Send your .tsx, .ts, or wagmi config with curl. Works with local Ollama (:11434) or this site's /api/wagmi proxy.

   curl --data-binary @app.tsx

2. 02

   Local LLM inference

   Ollama runs the Wagmi model on your GPU/CPU while the system prompt walks through hooks, chains, and viem calls.

   ollama · temperature 0.15

3. 03

   JSON report

   Structured JSON with severity, file location, Wagmi pattern ID, and suggested fixes — ready for jq, CI, and dashboards.

   format: "json"

Quick start · curl

Automate Wagmi reviews with local AI in 5 minutes

Pick a model and OS — the curl commands below update automatically. Copy them in order to plug AI into your editor, scripts, or CI.

Live example

Feed it a buggy hook, get a report like this

Reviewing a swap component with a missing chain guard and stale balance read using wagmi-coder:7b.

import { useAccount, useReadContract, useWriteContract } from 'wagmi'
import { erc20Abi } from 'viem'

export function useSwap(token: `0x${string}`) {
  const { address } = useAccount()

  const { data: balance } = useReadContract({
    address: token,
    abi: erc20Abi,
    functionName: 'balanceOf',
    args: [address!],
  })

  const { writeContract } = useWriteContract()

  const swap = () =>
    writeContract({
      address: token,
      abi: erc20Abi,
      functionName: 'approve',
      args: ['0xRouter...', balance ?? 0n],
    })

  return { balance, swap }
}

{
  "model": "wagmi-coder:7b",
  "report": {
    "quality_score": 88,
    "findings": [
      {
        "severity": "high",
        "title": "Missing chainId on writeContract",
        "line": 24,
        "pattern": "wagmi/write-chain-guard",
        "recommendation": "Pass chainId from useChainId() or use useWriteContract({ mutation: { onError } }) with simulate first."
      },
      {
        "severity": "medium",
        "title": "Stale balance after wallet switch",
        "line": 11,
        "pattern": "tanstack/query-key-account",
        "recommendation": "Include address and chainId in TanStack Query key via wagmi's queryKey helper."
      }
    ]
  }
}

API reference

Two endpoints, one schema

Call Ollama (http://localhost:11434) directly, or use the Wagmi AI proxy for a simpler request.

• POST/api/wagmi

  Takes TS/TSX source, reviews with Ollama, returns JSON report

  Wagmi AI
• GET/api/models

  Available models and Modelfile download URLs

  Wagmi AI
• GET/api/modelfile/:slug

  Modelfile for ollama create (text/plain)

  Wagmi AI
• POST/api/chat

  Chat request — pass source in the messages array

  Ollama
• POST/api/generate

  Single-prompt request — for testing short snippets

  Ollama

curl -s http://localhost:11434/api/chat -d '{
  "model": "wagmi-coder:7b",
  "stream": false,
  "format": "json",
  "messages": [
    {
      "role": "user",
      "content": "Review this Wagmi React component for hook and viem best practices.\n\n<file contents>"
    }
  ]
}' | jq -r '.message.content' | jq .

#!/usr/bin/env bash
set -euo pipefail
MODEL="wagmi-coder:7b"
for f in src/**/*.tsx; do
  report=$(curl -sf -X POST "$SITE/api/wagmi?model=$MODEL" \
    -H "Content-Type: text/plain" --data-binary @"$f" | jq -r '.report.quality_score')
  if [[ "$report" -lt 70 ]]; then
    echo "Wagmi review failed for $f (score $report)"
    exit 1
  fi
done

FAQ

Frequently asked questions