wigolo
Local-first web search, fetch, crawl, extraction and research for AI coding agents, without API keys.
Sources and review
Checked against public documentation on . Suitability guidance is our editorial judgment; this is not a performance benchmark or an endorsement.
Giving a coding agent web search and page fetching without a paid search API.
You need a stable release; the project describes itself as a public beta.
About wigolo
wigolo gives an agent one interface for web work: search, fetch, crawl, extract, cache, find-similar and multi-step research. It runs locally next to the agent as an MCP server, and also as a REST API with TypeScript and Python SDKs and integrations for LangChain, CrewAI, LlamaIndex, the Vercel AI SDK and n8n. Core tools need no API key; a free key is recommended for its research tool.
wigolo is listed in this index written primarily in TypeScript, with 5.5k stars on GitHub. Its latest recorded repository push was in November 2026; that is not an ASE editorial review date.
Before connecting: access and data
This record's specific permissions have not been reviewed by ASE. Read the publisher's documentation before copying setup or connecting.
- List the accounts, files and services the enabled tools can read, change or execute. Check your actual credentials and discovered tools.
- Use narrowly scoped credentials and read-only mode where supported. Review proposed writes before approving them; a generated configuration does not apply these limits for you.
- Local launch is not local-only data processing. External services receive requests, and your client may pass tool results to its model provider. Check both destinations before sharing private data.
- Keep keys and browser session files out of shared config, repositories and screenshots. Know how to disconnect the server and separately revoke its credentials or account sessions.
npx wigolo init