@specstream/langchain
v0.1.2
Published
The live web data engine for LangChain.js: Search API ($5 per 1,000 searches), Extract API ($0.80 per 1,000 pages) and Deep Search.
Maintainers
Readme
@specstream/langchain
SpecStream is the live web data engine for teams and agents. One platform to build, search, extract, enrich, map, and monitor data across the entire web.
Ask for any dataset in plain words, and SpecStream builds it from the entire live web: every match found, extracted and enriched into structured records, then monitored for change. It runs through the API and MCP, and inside Sheets, CRMs, Slack, n8n, Zapier and the other tools teams already use.
Source URL and read time on every value.
Three products:
- Search API:
GET /v1/web-search, $5 per 1,000 searches. The most accurate web search API in the world (scores and method: https://specstream.ai/benchmarks). - Extract API:
POST /v1/extract, up to 20 URLs a call (web pages, PDF, Word, Excel), $0.80 per 1,000 pages. A page with no text is not charged. - Deep Search: Ask in plain words. Get every match on the live web, in structured rows. Priced per row.
Install
npm install @specstream/langchain @langchain/core
export SPECSTREAM_API_KEY=ss_live_... # Agents & API in your SpecStream workspaceA free account comes with $10 of credit and needs no card: specstream.ai.
Tools
Both tools are LangChain StructuredTool classes, built like @langchain/tavily.
| Tool | Name | What it does | Cost |
| --- | --- | --- | --- |
| SpecStreamSearch | specstream_search | Calls GET /v1/web-search and returns the answer, matching rows and ranked sources, with page passages when passages: true | $5 per 1,000 searches |
| SpecStreamExtract | specstream_extract | Calls POST /v1/extract and returns the main text, title and published date of 1 to 20 web pages, PDF, Word or Excel files | $0.80 per 1,000 pages (a page with no text is free) |
Each tool takes specstreamApiKey (default: the SPECSTREAM_API_KEY environment variable), apiBaseUrl, name and description. A failed call returns { error } to the model.
MIT licensed.
