Integrations / Agent frameworks & builders
SpecStream for LangChain
langchain-specstream adds tools and a retriever to LangChain, so your agent can ask for data in plain words and get every match from the live web, under a price cap the model can't raise.
What you get
- Documents a chain can citeSpecStreamRetriever turns each match into a Document with its facts in page_content and its source_url in metadata.
- The cap stays in PythonWhen a quote tops max_price_usd, the agent gets the price back and can ask for fewer rows or tell the user.
- Schedules through MCP adaptersLoad the whole SpecStream server with langchain-mcp-adapters when the agent should also keep results current, export them, or fill in records you already hold.
Set it up
- Run pip install -U langchain-specstream on Python 3.10 or later, with LangChain 0.3 or 1.x.
- Export SPECSTREAM_API_KEY with a key made under Agents & API in SpecStream.
- Pass specstream_tools(max_price_usd=5) to create_agent, or call SpecStreamRetriever from a chain.
The full setup guide has every step, with what to do if something doesn’t arrive.
Related integrations
See all- OpenAI APILive web records as an MCP tool in the Responses API
- LlamaIndexA tool spec and retriever nodes for LlamaIndex agents
- CrewAILive web rows for the agents in your crew
- VercelAI SDK tools in TypeScript, plus a client for route handlers
- HaystackHaystack Documents from the live web, for pipelines and agents
- BotpressComing soonHub actions that put live web rows in a bot's reply
Live web data, in LangChain
Ask in your own words for companies, places, people, filings or anything else the web lists. You see the price before anything runs and pay only for the matches.