No written verdict yet. Here is what commenters said.

5recommend
3warn against
Dec 18, 2025first mention
Sep 28, 2026latest mention
Nov 25 – Oct 26
Used forprompt optimizationllm program optimizationllm programmingprompt optimization for agentsprompt optimization with evalsllm programming in production

Why people recommend it

“your agentic workflows are already using them”

Show 3 more

“Model testing and swapping is one of the surprises people really appreciate DSPy for.”

“I like to look at it like the MVC for the Web.”

Caveats and dissent

“I think a problem to DSPy is that they don't know the concept of THE WHOLE PRODUCT”

“I used dspy in production, then reverted the bloat as it literally gave me nothing of added value in practice but a lot of friction”

Show 1 more

“I think it takes the "prompt is a parameter" concept a bit too far.”

Often compared with

Who recommends it in their own words

From the makers not counted in the ranking

“I made a dspy fork where you can add a decorator”

All comments 20

“your agentic workflows are already using them”

“Is this comparable to https://dspy.ai/ ?”

“I know you can somewhat hillclimb via DSPy but that's hard to generalize.”

“this is essentially what Dspy does”

I'm surprised to see nanobot uses LiteLLM: https://github.com/HKUDS/nanobot LiteLLM wouldn't be my top choice, because it installs a lot of extra stuff. https://news.ycombinator.com/item?id=43646438 But it's quite popular.

“DSPy is cool from an integrated perspective but as someone who extensively develops agents, there have been two phases to the workflow that prevented me from adopting it”

“Model testing and swapping is one of the surprises people really appreciate DSPy for.”

“I think a problem to DSPy is that they don't know the concept of THE WHOLE PRODUCT”

“I used dspy in production, then reverted the bloat as it literally gave me nothing of added value in practice but a lot of friction”

“I think it takes the "prompt is a parameter" concept a bit too far.”

“Has anyone contrasted gas town to Stanford's DSPY”

“I like to look at it like the MVC for the Web.”

“using DSPy and an optimization algo GEPA”

Threads where it came up

Data: dspy.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.

Keyboard shortcuts
j / kNext / previous item
o or EnterOpen selected item
/Search
g hHome
g tTop
g rRising
g cCategories
tToggle dark mode
?This help