Integrations

Hub: documentation home · Python API · Getting started.

Two ways to use a tools.yaml. Pick the one your product supports.

You are building…	Use	Install
A Python agent (LangChain, LangGraph, OpenAI Agents, Anthropic SDK)	load_tools / connect in-process	Store extra (qdrant / pgvector / … — vector stores) plus langchain / langgraph / openai-agents / anthropic as listed below
A chat / IDE host (Claude Desktop, Claude Code, Codex, Cursor)	vectorsmith serve as an MCP server	Store extra so vectorsmith is on PATH

Same YAML either way. Do not import Engine. Field-by-field: tools.yaml.

MCP hosts

• Claude Desktop
• Claude Code
• OpenAI Codex (CLI, IDE extension, ChatGPT desktop Codex)
• Cursor
• claude.ai custom connector (serve --http)

Copy-paste configs: examples/mcp_hosts/.

Agent frameworks

• LangChain — from vectorsmith import load_tools
• LangGraph — same tools; create_react_agent / ToolNode
• OpenAI Agents SDK — from vectorsmith.openai_agents import load_tools
• Anthropic Messages API — from vectorsmith.anthropic import load_tools
• Other frameworks — LlamaIndex, CrewAI, raw connect()

One-liners

from vectorsmith import load_tools          # LangChain / LangGraph
from vectorsmith.openai_agents import load_tools
from vectorsmith.anthropic import load_tools

from vectorsmith import connect             # await vs.call("search_invoices", {…})

vectorsmith serve tools.invoices.yaml --name invoices