# yokingma/SearChat

Search + Chat = SearChat(AI Chat with Search), Support OpenAI/Anthropic/VertexAI/Gemini, DeepResearch, SearXNG, Docker.  AI对话式搜索引擎，支持DeepResearch, 支持OpenAI/Anthropic/VertexAI/Gemini接口、聚合搜索引擎SearXNG，支持Docker一键部署。

Repository: https://github.com/yokingma/SearChat
Canonical: https://ross.abutalabs.com/products/searchat
Homepage: https://isou.chat
Language: TypeScript
License: MIT
License Family: permissive
Topics: rag, search, deepresearch, searxng, ai, llm, mcp, anthropic, gemini, vertexai, openai
Last push: 2026-08-31T02:28:34+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 83, longevity 64
- inputs: {"age_days": 908, "days_push": 3, "days_rel": 112, "gap_med": 7.0, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1059, forks 181 (observed 2026-09-01T02:14:08.594766+00:00)

## What it is
SearChat is a self-hostable AI-powered conversational search engine that combines web search (Bing, Google, SearXNG) with multi-turn chat backed by OpenAI, Anthropic, Gemini, and VertexAI models. It includes a Deep Research mode built on LangChain/LangGraph for iterative exploration and structured report generation, and deploys via Docker.

## Use cases
- self-host an AI search engine like perplexity
- chat with search results using my own OpenAI or Anthropic key
- run a private conversational search with SearXNG
- generate deep research reports automatically from web sources
- deploy an AI answer engine with docker
- multi-turn web search chatbot with multiple LLM providers

## When to choose
- you want a self-hosted Perplexity-style AI search with your own API keys
- you need SearXNG aggregation or multi-provider LLM support
- you want Docker one-click deployment and browser-local chat history

## When to avoid
- you need MCP tool integration or image/video search today (still TODO)
- you need document upload and file parsing (not yet implemented)
- you want a fully managed hosted service rather than self-hosting

## Facets
- artifact type: application
- maturity: active
- function: search-engine, rag, chatbot, web-framework, llm-inference, agent-framework
- domain: artificial-intelligence, large-language-models, web-development
- platform: self-hosted, cross-platform
- tags: conversational-search, searxng, deep-research, ai-search-engine, multi-model, turborepo, vue3, koa, search, retrieval-augmented-generation, nodejs, docker, web-server

## Member repositories
- yokingma/SearChat (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:14:08.594766+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 2026-08-30T06:57:53.313603+00:00, confidence not recorded.
  - readme: https://github.com/yokingma/SearChat (fetched 2026-09-01T02:14:08.594766+00:00, sha 199c950ab10e)
  - homepage: https://isou.chat (fetched 2026-08-29T12:59:30.521303+00:00, sha 51a45ac6cf78)
- Data as of 2026-08-30T08:39:29.467469+00:00.