Comparisons / AutoGen vs DSPy

AutoGen vs DSPy: Which Agent Framework to Use?

AutoGen by Microsoft models agents as ConversableAgents that chat with each other. DSPy replaces hand-written prompts with compiled modules. Here is how they compare — paradigm, ecosystem, and the use cases each one is actually built for.

By the numbers

AutoGen

GitHub Stars

56.7k

Forks

8.5k

Language

Python

License

CC-BY-4.0

Created

2023-08-18

Created by

Microsoft Research

github.com/microsoft/autogen

DSPy

GitHub Stars

33.4k

Forks

2.8k

Language

Python

License

MIT

Created

2023-01-09

Created by

Stanford NLP (Omar Khattab)

github.com/stanfordnlp/dspy

GitHub stats as of April 2026. Stars indicate community interest, not necessarily quality or fit for your use case.

ConceptAutoGenDSPy
Agent`ConversableAgent` with `system_message`, `llm_config``dspy.ReAct` module with signature and tools
Tools`register_for_llm()` and `register_for_execution()`Tools passed to `ReAct` module as callable list
ConversationTwo-agent chat with `initiate_chat()`, message history
Multi-Agent`GroupChat` with `GroupChatManager`, speaker selection
Nested Chats`register_nested_chats()` for sub-task handling
Termination`is_termination_msg` callback, `max_consecutive_auto_reply`
Prompts`dspy.Signature` defines input/output fields, compiled to optimized prompts
Optimization`dspy.BootstrapFewShot`, `MIPROv2` auto-tune prompts against a metric
Chaining`dspy.ChainOfThought`, `dspy.Module` with `forward()` composition
Evaluation`dspy.Evaluate` with metric functions and dev sets

AutoGen vs DSPy, head to head

AutoGen AutoGen by Microsoft models agents as ConversableAgents that chat with each other.

DSPy DSPy replaces hand-written prompts with compiled modules.

Both wrap the same underlying agent pattern — an LLM call, a tool dispatch, a loop — in different abstractions. The choice between them is mostly about which mental model and ecosystem fits the team you have, not which one is technically more capable.

Pick AutoGen if

Pick AutoGen if autoGen excels at complex multi-agent workflows where agents need to debate or collaborate. For single-agent use cases or simple tool-calling agents, the plain Python version is significantly simpler. AutoGen is the right fit when the tradeoffs in its intro line up with how your team actually wants to work day-to-day; DSPy would force you to translate.

Full AutoGencomparison →

Pick DSPy if

Pick DSPy if dSPy's real innovation is automated prompt optimization — replacing manual prompt engineering with algorithmic tuning. This is genuinely novel and valuable for production systems where prompt quality matters at scale. For simple agents or learning, hand-written prompts are easier to understand and modify. DSPy is the right fit when the tradeoffs in its intro line up with how your team actually wants to work day-to-day; AutoGen would force you to translate.

Full DSPycomparison →

What both add

Both AutoGen and DSPy pull in a class hierarchy and a dependency tree to wrap what is, at the core, an HTTP POST in a while loop. If your use case is straightforward — one provider, a handful of tools, a single agent — the framework cost may exceed the framework benefit. The lesson below shows the same pattern in ~60 lines without either dependency.

Or build your own in 60 lines

Both AutoGen and DSPy implement the same 8 patterns. An agent is a function. Tools are a dict. The loop is a while loop. The whole thing composes in ~60 lines of Python.

No framework. No dependencies. No opinions. Just the code.

Build it from scratch →