Ross ROSS = Recommend OSS · open-source software intelligence for agents

karust/openserp

Self-hosted SERP API for AI, SEO & automation. Browser-rendered Google, Bing, Yandex, Baidu, DuckDuckGo and Ecosia search with page extraction 🎉 observed · 2026-08-28

github.com/karust/openserp · homepage · Go · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

91/100

  • Activity 93
  • Release rhythm 94
  • Longevity 83
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 22.5
  • age_days: 1168
  • days_rel: 42
  • days_push: 42
  • n_releases_24m: 11

Full methodology

Adoption not part of the score

1306 stars · 151 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

OpenSERP is a self-hosted, MIT-licensed SERP API and CLI written in Go that returns structured search results from Google, Bing, Yandex, Baidu, DuckDuckGo, and Ecosia via browser rendering, with no API keys or per-search billing. It offers multi-engine megasearch, page content extraction to markdown, SERP feature capture, image search, and a hosted cloud version with SDKs and an MCP server.

Use cases

  • scrape google search results as json without an api key
  • give llm agents live web search grounding
  • track keyword rankings across google bing and yandex for seo
  • extract page content as markdown for rag pipelines
  • query multiple search engines at once and merge results
  • self-host a serpapi alternative in docker
  • search yandex baidu and duckduckgo programmatically

When to choose

  • you need structured SERP data from engines beyond Google, especially Yandex, Baidu, or Ecosia
  • you want a free self-hosted search backend for LLM agents, RAG grounding, or SEO rank tracking
  • you want one consistent JSON schema across six engines plus page extraction in a single call

When to avoid

  • you need guaranteed SLA-backed results at high volume without managing browser infrastructure or proxies
  • you only need a simple search API and don't want to run any servers - the managed cloud or a commercial SERP API may be simpler
  • your use case violates search engines' terms of service or requires fully compliant official APIs

Facets

service · maturity active

search-engine web-scraping http-server cli api-framework rag web-development developer-tools crawlers large-language-models self-hosted go cli cross-platform serp-api seo rank-tracking browser-rendering megasearch llm-grounding mcp-server docker self-hosted search-api search automation web-server

9 sources

Member repositories

RepositoryRoleHealth v2
karust/openserpmain91

For agents

markdown · JSON · MCP: product_card(name="karust/openserp")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem