# searcharvester

> Self-hosted search API and deep research tool for AI agents with Tavily-compatible endpoints, SearXNG metasearch, and a live web UI.

- **Category:** AI Agents
- **Licence:** AGPL-3.0
- **Latest version:** 2.1.0
- **Open source:** oss
- **Languages:** Typescript, Python
- **Platforms:** Docker Compose
- **Tags:** Search, Markdown, Ai Agents, Web Scraping, Agentic Ai, LLM, Rag, Searxng, Docker, Docker Compose, Fastapi, Self Hosted, Tavily, Deep research, Search api, Llm Tools, Trafilatura, Markdown Extraction

## Description

Searcharvester is a self-hosted stack that gives AI agents a Tavily-compatible search API backed by SearXNG with over 100 engines, a URL-to-markdown extractor using multiple extraction engines with size presets and pagination, and a deep research agent that plans, searches, reads, and synthesizes cited markdown reports. It includes a React web UI on port 9762 to start jobs, pick models per agent role, watch agents live, and browse sources and media. The stack runs with one docker compose up, pulling the adapter image from GHCR and building the UI and search-admin locally. No API keys or quotas for search; LLM credentials (any OpenAI-compatible endpoint) are only needed for the research feature. The adapter listens on 127.0.0.1:8000, SearXNG on 8999, search-admin on 8011, and the UI on 9762. Licensed AGPL-3.0 with MIT on project code.

## Links

- [Homepage](https://github.com/vakovalskii/searcharvester)
- [Docker](ghcr.io/vakovalskii/searcharvester)
- [GitHub Repository](https://github.com/vakovalskii/searcharvester)
- [Documentation (English)](https://github.com/vakovalskii/searcharvester/tree/main/docs/en)
- [Documentation (Russian)](https://github.com/vakovalskii/searcharvester/tree/main/docs/ru)
- [Documentation (Chinese)](https://github.com/vakovalskii/searcharvester/tree/main/docs/zh)

---
Source: https://selfhost.directory/project/searcharvester