Integrations
Bring finished web results into the stack you already run.
Search gives your model sources. Tabstack builds the cited answer and returns it inside the stack you already use. Add clean page content, matching JSON, or public web tasks when the workflow needs them.
Recommended paths
Start with the path that matches how you build.
Python SDK
For applications, scripts, and model stacks built in Python that need Tabstack to build a cited answer from web sources.
CLI
For terminal workflows, coding agents, shell-based automation, and a quick first call.
Hermes Agent
For Hermes users who want cited answers without making Hermes build them from search results, plus a Tabstack-backed extraction path.
LangChain
For TypeScript or Python agents that need native Tabstack tools, including Research that returns a cited answer instead of sources for the model to process.
More integrations
More frameworks Tabstack plugs into.
Each card links to its install guide.
Vercel AI SDK
Typed tool() definitions that pass straight to generateText and streamText, backed by the Tabstack SDK.
OpenAI Agents
Pre-built tool() definitions you hand straight to an Agent, backed by the Tabstack SDK.
Claude Agent
Pre-built Tabstack tools you wire into a Claude Agent SDK query() call.
Mastra
Typed createTool definitions that spread straight into a Mastra Agent, backed by the Tabstack SDK.
LlamaIndex
Pre-built tool() definitions you pass straight to a LlamaIndex.TS agent, backed by the Tabstack SDK.
eve
Pre-built defineTool definitions you re-export into agent/tools/ for cited answers, clean Markdown, matching JSON, and public web tasks in eve agents.