Use the framework you want. Let Weavz own the action layer.
Your framework decides how the agent plans, reasons, branches, and hands off. Weavz gives it scoped app access, user-owned credentials, MCP servers, durable state, files, approvals, and audit receipts.
Weavz plugs in where frameworks expect tools.
Use MCP when your harness can consume a remote server. Use the TypeScript or Python SDK when you want framework-native tool definitions backed by Weavz action execution.
OpenAI Agents SDK
Build agent orchestration in code and attach Weavz as a hosted MCP tool source.
You build agents in OpenAI code and need a governed tool source.
LangGraph
Use Weavz MCP endpoints inside stateful graph workflows and long-running agent flows.
Your agent workflow is a graph with durable branches and state.
LangChain
Load Weavz tools through MCP adapters or route SDK tool calls back through Weavz.
You already use LangChain tools, adapters, or chains.
CrewAI
Give crews controlled business actions without embedding customer credentials in prompts.
You coordinate role-based crews that need app access.
Google ADK
Connect ADK agents to Weavz over Streamable HTTP MCP or generated SDK tools.
You are building with Google ADK and want hosted business tools.
Microsoft Agent Framework
Use Weavz as the governed action layer behind Microsoft-stack agent apps.
Your agents live in a Microsoft-stack application or service.
AutoGen / AG2
Attach scoped Weavz workspaces to conversational multi-agent systems.
You need multi-agent conversations with scoped business actions.
Semantic Kernel
Call Weavz from planner and plugin-style workflows where business actions need audit.
You use planner or plugin-style enterprise orchestration.
LlamaIndex Workflows
Pair document-heavy agents with governed actions, files, state, browser, and approvals.
Your agent starts with documents, indexes, or retrieval workflows.
Mastra
Use a TypeScript-first agent stack while Weavz handles app access and user auth.
You want a TypeScript agent app with hosted tool execution.
Vercel AI SDK
Convert Weavz action tools into AI SDK tool sets for app-owned agent loops.
Your product loop is built with Vercel AI SDK tools.
Pydantic AI
Keep Python agents type-safe while Weavz validates and executes app actions.
You want typed Python agents with validated tool inputs.
Agno
Run lightweight Python agents against Weavz-hosted app actions and state.
You are shipping compact Python agents and need external actions.
Haystack
Add governed actions to retrieval and document pipelines when agents need to act.
Your pipeline retrieves information and then needs to take action.
smolagents
Give code-first agents a scoped MCP endpoint instead of raw customer credentials.
You want lightweight code agents with a narrow action boundary.
DSPy
Keep prompt/program optimization separate from the runtime that touches business apps.
You optimize language programs but do not want raw credentials in them.
Claude Agent SDK
Use Weavz through MCP when Claude-based agents need customer app access.
You are building Claude-based agents and want remote MCP tools.
Custom MCP clients
Any Streamable HTTP MCP client can receive a workspace endpoint and scoped mcp_ token.
You built your own MCP client, IDE harness, or agent runtime.
Hand the harness an endpoint, not a pile of app credentials.
Your backend creates the workspace, end user, connect links, MCP server, and scoped token first. These snippets show only the framework handoff.
{
"mcpServers": {
"weavz-acme": {
"type": "http",
"url": "https://platform.weavz.io/mcp/srv_...",
"headers": {
"Authorization": "Bearer mcp_..."
}
}
}
}import { Agent, hostedMcpTool } from "@openai/agents";
const agent = new Agent({
name: "Customer ops agent",
tools: [
hostedMcpTool({
serverLabel: "weavz",
serverUrl: "https://platform.weavz.io/mcp/srv_...",
headers: { Authorization: "Bearer mcp_..." },
}),
],
});from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
client = MultiServerMCPClient({
"weavz": {
"transport": "http",
"url": "https://platform.weavz.io/mcp/srv_...",
"headers": {"Authorization": "Bearer mcp_..."},
}
})
tools = await client.get_tools()
agent = create_react_agent(model, tools)from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
weavz_tools = McpToolset(
connection_params=StreamableHTTPConnectionParams(
url="https://platform.weavz.io/mcp/srv_...",
headers={"Authorization": "Bearer mcp_..."},
)
)Provision first
Create workspaces, users, aliases, and connect links from your backend.
Use MCP for agents
Give the framework a remote MCP endpoint plus a scoped mcp_ token.
Keep control
Human Gates, state, files, triggers, and audit remain in the workspace.