Library / SDK
Agents & Orchestration
TextGrad
1Automatic 2differentiation 3through 4text 5for 6optimization
the six Ws · specification
W1
Who
Maintained by the Zou group at Stanford.
W2
What
Optimizes prompts and pipelines via textual gradient feedback.
W3
Where
A Python library on your infrastructure.
W4
When
When you want to automatically improve LLM pipelines.
W5
Why
Backpropagates natural-language critique to tune components.
W6
With
Python and an LLM provider.
W7
Watch
Academic open-source (MIT), library only. Runs locally and calls whichever LLM provider you configure.