# KnockOutEZ/wigolo

The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.

Repository: https://github.com/KnockOutEZ/wigolo
Canonical: https://ross.abutalabs.com/products/wigolo
Homepage: https://knockoutez.github.io/wigolo/
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: mcp, agent, ai, ai-agent, claude, cli, developer-tools, local-first, mcp-server, metasearch, model-context-protocol, nodejs, privacy, rag, search, search-engine, typescript, web-crawler, web-scraping, web-search
Last push: 2026-08-26T23:10:18+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 93, longevity 10
- inputs: {"age_days": 143, "days_push": 7, "days_rel": 45, "gap_med": 0, "n_releases_24m": 10}
- flags: young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4694, forks 346 (observed 2026-08-28T04:08:57.057714+00:00)

## What it is
wigolo is a local-first MCP server that gives AI coding agents web intelligence tools: search across 18 engines, fetch with anti-bot escalation, crawling, extraction, and a local vector cache. It runs as an MCP server, REST API, or SDK alongside agents like Claude Code, Cursor, and LangChain with no API keys or cloud dependency.

## Use cases
- give my coding agent web search without API keys
- let claude code fetch and read web pages locally
- crawl and extract content from websites for RAG
- self-hosted web search server for AI agents
- search multiple search engines and rerank results locally
- cache web content locally for agent research
- bypass anti-bot walls when fetching pages for my agent

## When to choose
- you want web search/fetch/crawl tools for an MCP-compatible agent with zero API keys or metered costs
- you need local-first, privacy-preserving web intelligence that runs on your own machine
- you want one unified tool surface (search, fetch, crawl, extract, cache) for multiple agents and frameworks

## When to avoid
- you need a fully managed, cloud-hosted search API with SLAs
- you require a permissively licensed dependency (it is AGPL-3.0)
- you need production-grade stability — it is in public beta

## Facets
- artifact type: service
- maturity: experimental
- function: search-engine, web-scraping, mcp, rag, http-client, caching, cli, http-server
- domain: artificial-intelligence, developer-tools, web-development, privacy, self-hosted
- platform: cli, self-hosted, cross-platform
- tags: mcp-server, local-first, metasearch, web-crawler, ai-coding-agents, no-api-keys, content-extraction, agpl, ai-agents, search, nodejs

## Member repositories
- KnockOutEZ/wigolo (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:57.057714+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:19:14.507049+00:00, confidence not recorded.
  - readme: https://github.com/KnockOutEZ/wigolo (fetched 2026-08-28T04:08:57.057714+00:00, sha b31d04005a54)
  - homepage: https://knockoutez.github.io/wigolo/ (fetched 2026-08-29T09:03:22.485868+00:00, sha 94d4c4b64297)
  - registry_npm: https://registry.npmjs.org/wigolo (fetched 2026-08-29T09:03:22.495447+00:00, sha 363baa55b591)
- Data as of 2026-08-30T08:39:29.467469+00:00.