google-research/cascades

Interactive Composition Explorer: a debugger for compositional language model programs

DSPy: The framework for programming—not prompting—language models

Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs, and tools — the model handles its own control flow. Get fully interpretable trajectories and performance that scales directly with model improvements. Without context rot.

Probabilistic programming with large language models

The LLM Anti-Framework

Harness LLMs with Multi-Agent Programming

Build data processing and data analysis pipelines that leverage the power of LLMs 🧠

Seamlessly integrate LLMs as Python functions

OO for LLMs