# fatwang2/search2ai

Help your LLMs online

Repository: https://github.com/fatwang2/search2ai
Canonical: https://ross.abutalabs.com/products/search2ai
Homepage: https://sum4all.site/telegram
Language: JavaScript
License: MIT
License Family: permissive
Topics: online, openai, openai-api, search, functioncalling, gemini, groq, llama, mistral, toolcall
Last push: 2026-08-03T00:32:42+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 64, longevity 70
- inputs: {"age_days": 990, "days_push": 31, "days_rel": 31, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1279, forks 190 (observed 2026-08-28T04:04:13.610959+00:00)

## What it is
A proxy service that adds online search, news, and webpage summarization capabilities to any OpenAI-compatible LLM API via function calling. Users simply point their existing clients at the search2ai endpoint instead of the upstream API, with no plugin installation or key changes required.

## Use cases
- add web search to chatgpt clients without plugins
- make my llm api search the internet
- proxy openai api with online search
- add news and webpage summaries to llm chatbots
- deploy a search-enabled openai-compatible endpoint on cloudflare workers
- let deepseek or groq models access the web

## When to choose
- you use OpenAI-compatible clients and want web search without changing apps or keys
- you want a self-hostable or Cloudflare Worker deployment
- you need streaming support and compatibility with multiple LLM providers like Gemini, Groq, DeepSeek, or Azure OpenAI

## When to avoid
- you need a full RAG pipeline with your own document corpus rather than live web search
- you want native provider search features like OpenAI's built-in browsing
- you cannot obtain an API key for a supported search service

## Facets
- artifact type: service
- maturity: active
- function: search-engine, agent-framework, http-server, middleware, llm-inference
- domain: large-language-models, artificial-intelligence, web-development, self-hosted
- platform: cloud, self-hosted
- tags: openai-compatible-proxy, web-search, function-calling, cloudflare-workers, rag, news, webpage-summarization, search, nodejs, web-server, docker

## Member repositories
- fatwang2/search2ai (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:13.610959+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 2026-08-30T05:02:41.214028+00:00, confidence not recorded.
  - readme: https://github.com/fatwang2/search2ai (fetched 2026-08-28T04:04:13.610959+00:00, sha 04b6fcf7759c)
  - homepage: https://sum4all.site/telegram (fetched 2026-08-29T12:13:31.050139+00:00, sha 91900a2cf3e7)
- Data as of 2026-08-30T08:39:29.467469+00:00.