AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Browser Automation/
wigolo
wigolo logo

wigolo

Active·★ 5.5k·NOASSERTION·Updated 2026-10-22
★ Trending

wigolo is a local-first web intelligence MCP server that the README says needs no keys, no cloud and no metered bill. It runs on your machine and gives a coding agent one surface for search, fetch, crawl, extract, cache, find-similar, research and an autonomous gather loop, plus diff and watch to see what changed on a page. One command installs the local engine and wires it into agents such as Claude Code, Cursor, Codex, Gemini CLI, VS Code, Windsurf, Zed and Antigravity: `npx wigolo init --non-interactive --agents=...`; `npx wigolo doctor` checks health. It needs Node 20 or newer and about 1.5 GB of disk.

The README describes search across 18 direct engine adapters with rank fusion and an on-device cross-encoder reranker, a tiered fetch router (HTTP, then TLS impersonation, then headless browser) that escalates on anti-bot challenges, crawling with per-domain rate limits and robots.txt respect, structured extraction against schemas, and a local cache with keyword and on-device vector search. Cache, embeddings, models and config live under ~/.wigolo/ and nothing leaves the machine unless you opt in to an LLM for synthesis. A comparison table against Firecrawl, Exa and Tavily, and a one-query benchmark, are the project's own and are dated July 2026. The project is in public beta.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-17.

License
Not detected by GitHub
Latest release
v0.2.1 · 2026-07-19
Last commit
2026-10-17
Contributors
11
Forks
450
Open issues and PRs
78
First published
2026-04-12
npm package
wigolo 0.2.1 · 677 downloads last week

Source: GitHub, npm and PyPI public APIs.

#Web Intelligence#AI Agent Tools#Local-first#Web Scraping#Search Engine#Data Extraction#MCP Protocol#Node.js
$ Install
$ npx wigolo init --non-interactive --agents=<your-agent>
↗ Visit site★ GitHub
01

Features

01Multi-engine web search with rank fusion and ML reranking.
02Tiered fetch router for loading URLs, auto-escalating on anti-bot challenges.
03Multi-page crawling with respect for robots.txt and rate limits.
04Structured data extraction from pages (tables, metadata, custom schemas).
05Local caching of all seen content for instant, offline re-query.
02

Why choose it

+Search, fetch, crawl, extract, cache, research and watch with no API key, all running on your machine.
+Tiered fetching escalates from plain HTTP to TLS impersonation to a headless browser when pages block simple requests.
+Local cache and on-device embeddings make repeat queries free and keep query data on your machine.
+One `npx wigolo init` command wires it into eight agents, with a `doctor` command to check health.
03

Trade-offs

!It is in public beta, and the comparison with Firecrawl, Exa and Tavily and the one-query benchmark are the project's own and dated July 2026.
!It needs about 1.5 GB of disk for the local engine, browser and models, and Node 20 or newer.
!Default search goes through public engines via direct adapters, so results depend on those engines staying accessible; GitHub shows the licence as NOASSERTION.
04

Maintenance check

ActiveChecked: 2026-10-20
Last commit
2026-09-27
Commits, last 90 days
100+
Releases, last 90 days
1
Latest release
binary-v0.2.1-sd507.1 (2026-09-08)
Open issues
78
Recent issues with at least one comment
2/16
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 6, 0, 0, 1, 0, 12, 3, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

05

Compatibility

Node.js
Runtime
Verified via docs
macOS
Operating System
Verified via docs
Linux
Operating System
Verified via docs
Windows
Operating System
Verified via docs
AI Agents (e.g., Claude Code, Cursor, VS Code)
Integration
Verified via docs
06

Quick start

1
$ npx wigolo init --non-interactive --agents=<your-agent>
07

Use cases

↳AI coding agents performing web research and information gathering.
↳Automated web content retrieval and structured data extraction for agents.
↳Building local-first knowledge bases from crawled web data.
↳Monitoring web page changes and receiving webhook notifications.
08

Alternatives

⚡Top VS:
VSPyScrappy★263→VSlinkedin-applicants-mcp★24→VSmcp-camoufox★21→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start

Most discussed open issues

  • #161 Chrome profile copy left unused3 comments · 2026-07-13
  • #303 search_engines parameter declared but never consumed (CLI --search-engines and MCP search_engines both ignored)2 comments · 2026-08-14
  • #231 ARM64 Docker image missing @anush008/tokenizers-linux-arm64-gnu → vector search silently degrades to rerank-only2 comments · 2026-07-22
  • #207 SSRF follow-up: pin the socket to the validated IP (DNS rebinding / TOCTOU)2 comments · 2026-07-19
  • #144 Add an npm registry search engine adapter2 comments · 2026-07-05

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

VS
tap
★18
→
PyScrappy logo
PyScrappy★ 263
Python web scraping toolkit and MCP server that gives AI agents clean, structured web data from any URL or built-in scrapers.
VSCompare→
linkedin-applicants-mcp logo
linkedin-applicants-mcp★ 24
MCP server that exports your LinkedIn job applicants (lists, resumes, profiles) through your own Chrome, paced like a person, with a local dashboard
VSCompare→
mcp-camoufox logo
mcp-camoufox★ 21
MCP server for stealth browser automation via Camoufox — 100+ tools, npx install, anti-bot stealth
VSCompare→
tap logo
tap★ 18
Capture a logged-in browser task once — replay it forever at zero LLM tokens. Local-first browser-automation MCP for Claude Code, Cursor & any MCP host; credentials never leave your machine.
VSCompare→
firecrawl-mcp-server logo
firecrawl-mcp-server★ 7.7k
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
VSCompare→
crw logo
crw★ 1.2k
Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.
VSCompare→
cloakbrowser-mcp logo
cloakbrowser-mcp★ 169
⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.
VSCompare→
docs-mcp-server logo
docs-mcp-server★ 1.8k
Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools
VSCompare→
See all alternatives →
07
Use cases
08Alternatives
KnockOutEZ /
wigolo
↗

Keyless local MCP server for web search, fetch, crawl and research

5.5k450
Last commit1d ago
StatusActive
CategoryBrowser Automation
Contributors11
Latest releasev0.2.1
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit