Stanford NLP
DSPy
Framework for programming language models with declarative modules and optimizers, including ReAct-style tool-using agents.
Install
Run in your terminal
pip install dspy
Latest version read from pypi package dspy.
Multi-agent patterns
Handoffs
One agent passes the conversation to another agent, which takes over.
Not shown in the docs.
Subagents / agents as tools
A main agent calls other agents like tools and gets their result back, each with its own context.
Not shown in the docs.
Graph or workflow
You define steps and edges (or a workflow), and the framework runs agents and functions through them.
Not shown in the docs.
Group chat / crew
Several agents with roles work together on a task, coordinated by a manager or a selection rule.
Not shown in the docs.
Human in the loop
The run pauses for a person to approve, edit or answer before it continues.
Not shown in the docs.
Protocols and hosting
Hosted runtime
Self-hosted only (none documented)
Questions
Does DSPy support MCP?
Yes. DSPy's documentation shows agents using tools from MCP servers.
Does DSPy support the A2A protocol?
Its documentation does not cover A2A as of 2026-10-07.
What multi-agent patterns does DSPy support?
The docs do not show a multi-agent pattern; it focuses on single agents or programs.
Links
Alternatives in the same languages
Get the weekly agent stack update
New official MCP servers, spec changes and harness releases, checked against the source. One email a week, no fluff.
Reviewed Oct 7, 2026.