Inspect: A framework for large language model evaluations

A neurosymbolic framework for vulnerability detection in code

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

Data and Code for Program of Thoughts [TMLR 2023]

Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds secure-by-default practices into AI coding workflows (generation and review). It ships core security rules, tran…

[NeurIPS 2025] PIPS: Per-Instance Program Synthesis

[NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

A high-throughput and memory-efficient inference and serving engine for LLMs

🤗 smolagents: a barebones library for agents that think in code.

Instruction Following by Boosting Attention of Large Language Models

FIX 2.0: Features Interpretable to Experts (extended to include black-box LLM explanations)

Dolphin is a Python package that enables scalable neurosymbolic learning by performing probabilistic computations over the GPU.

A unified interface for using various LLMs

Representation Engineering: A Top-Down Approach to AI Transparency

TorchQL is a query language for Python-based machine learning models and datasets.

Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

Code and data accompanying our paper on arXiv "Faithful Chain-of-Thought Reasoning".