← back to the directory
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.

OptimizationPromptingPython

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.