verifier.org

DSPy

not quite an agent framework — a prompt/program optimizer

free — MIT (open source)#teams-optimizing-pipelin

included honestly and ranked low on this axis on purpose: dspy programs and optimizes llm pipelines rather than orchestrating agents. it's complementary to everything above, not a competitor.

dspy from stanford nlp is a framework for programming and optimizing llm pipelines — signatures and modules plus automatic prompt/weight optimizers like mipro and gepa, a reflective evolutionary optimizer that reportedly beats rl methods with far fewer rollouts. it's production-used and can build react agents, but reliability and durability aren't its focus; its optimized prompts often feed the other frameworks on this list.

that's why it ranks low here specifically — it's the wrong tool if you want an orchestration runtime, and the right tool if you want to squeeze quality out of a pipeline. cross-provider, and genuinely valuable at what it actually does.

the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.

pricing
free — MIT (open source)
website
github.com
our verdict

included honestly and ranked low on this axis on purpose: dspy programs and optimizes llm pipelines rather than orchestrating agents. it's complementary to everything above, not a competitor.

we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.

more ai agent frameworks

AutoGPT

the original autonomous agent project, now a self-hostable platform

#open-source#platform

Haystack

deepset's pipeline framework for rag and agents in python

#python#rag

Semantic Kernel

microsoft's sdk for c#, python and java, now beside the agent framework

#dotnet#microsoft

Atomic Agents

small composable agent library built on pydantic and instructor

#python#minimal