mcp-server

wigolo: AI Coding Agent Web

Get local-first search and research for your AI coding agent with wigolo.
5,099 stars404 forksTypeScriptGuide quality 9/10Updated 9/6/2026100% free · open source
What it does

Wigolo provides local-first search and research capabilities for AI coding agents using MCP, allowing for cloud-free and cost-effective querying.

When to use it
  • When you need to integrate AI-powered search and research into your MCP-based application without incurring cloud costs
  • When you want to keep your data local and avoid API key management for your AI coding agent
  • When you're using MCP and need a public beta solution for local-first search, fetch, crawl, and research
Ready-to-paste prompt
Use the example queries provided in the wigolo repository's documentation to perform a local-first search, such as querying for specific code snippets or documentation within your MCP project
Heads up: Ensure you have Node.js and a compatible TypeScript version installed, as wigolo is built with TypeScript and may require specific runtime environments to function correctly
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/wigolo && curl -fsSL https://workflowstacks.com/api/skills/wigolo/claude-skill -o ~/.claude/skills/wigolo/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How wigolo: AI Coding Agent Web works
Codeflow
Free to inspect

Wigolo: AI Coding Agent Web is a very large TypeScript project (~88k lines across 543 code files, plus 768 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.

Size
Very large codebase
~88k lines · 543 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js · Docker
No API keys detected
TypeScript 95%Python 3%Shell 1%JavaScript 1%CSS 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    SKILL.md
    The instructions the AI actually follows
  3. 3
    src/index.ts
    Where the program starts running
  4. 4
    package.json
    Dependencies and the commands it exposes
  5. 5
    examples/README.md
    A worked example — copy this to get going
What's in each folder
src/Core code — the actual logic429 files
skills/Prompts, skills & agent definitions13 files
site/Frontend / UI83 files
packages/Sub-packages / plugins42 files
examples/Examples you can copy30 files
docs/Documentation13 files
benchmarks/Evaluations & benchmarks50 files
sdks/SDKs / client libraries45 files
READMEHas testsDocumentedCI checksDocker readyExamples includedOther licenseUpdated this month
Quick Actions
Details
Creator
KnockOutEZ
Language
TypeScript
Category
mcp-server
Published
4/12/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.