Build LLM-powered agents
with production-ready TypeScript

DSPy for TypeScript. Working with LLMs is complex—they don't always do what you want. DSPy makes it easier to build amazing things with LLMs. Just define your inputs and outputs (signature) and an efficient prompt is auto-generated and used. Connect together various signatures to build complex systems and workflows using LLMs.

15+ LLM Providers

End-to-end Streaming

Auto Prompt Tuning

AxACEOptions

Defined in: https://github.com/ax-llm/ax/blob/0aa4aa2ceed1ba61106711baed6ce962cf2eb604/src/ax/dsp/optimizers/aceTypes.ts#L94

Configuration options specific to ACE inside Ax.

Properties

Property	Type	Description
`allowDynamicSections?`	`boolean`	Whether to automatically create sections when curator emits new ones.
`initialPlaybook?`	`AxACEPlaybook`	Initial playbook supplied by the caller.
`maxEpochs?`	`number`	Maximum number of epochs for offline adaptation.
`maxReflectorRounds?`	`number`	Maximum reflector refinement rounds (paper uses up to 5).
`maxSectionSize?`	`number`	Maximum bullets allowed in any section before triggering pruning.
`similarityThreshold?`	`number`	Optional similarity threshold used by the semantic deduper.