NFS-safe persistent dictionary for Python

Prodigy and Schedule-Free, together at last.

Code repository for the HAIPS 2025 paper: "LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data"

WinMute lets you automatically mute your PC volume on certain events (e. g. Screensaver, Workstation Lock, Shutdown, etc.).

Automatic theorem proving via natural language reasoning with LLMs

Python API for lightweight communication with the Rocq proof assistant

Python nested loops as classes for improved readability and modularity

Code for the paper "TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods".

Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization

Interpret text data with LLMs (sklearn compatible).

Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)

Procedural symbolic reasoning data generators suite for synthetic pretraining

[AAAI 2026] - Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"

Generate random nonsense math papers

GQR, a Fast Reasoner for Binary Qualitative Constraint Calculi

Efficient and multi-language generation from context free or sensitive grammars (CFG/CSG)

Efficient few-shot learning with Sentence Transformers

Datasets collection and preprocessings framework for NLP extreme multitask learning

A web interactive tool for building proofs in the sequent calculus of Linear Logic, with its backend written in OCaml

Generate audiobooks from e-books, voice cloning & 1158+ languages!

A SAT based Theorem Prover for Modal Logic K.

A graphical MLL+MIX theorem prover and proof net library

LLM101n: Let's build a Storyteller

Comprehensive LLM evaluation framework: GPQA Diamond to Chatbot Arena. Tests all major models equally, easily extensible.

A curated collection of LLM reasoning and planning resources, including key papers, limitations, benchmarks, and additional learning materials.

Code for the paper "TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods".

Adds multiprocessing capabilities to Pandas to parallelize apply operations on DataFrames, Series and DataFrameGroupBy

Comfortable parallel TQDM using concurrent.futures