A reconstruction of the benchmark behind Luc Julia's notorious 64% accuracy rate for LLMs.

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

🃏 A python implementation of a General Game Playing (GGP) framework.

Public benchmark releases for Concept Synth

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀

The context API to search, scrape, and interact with the web at scale. 🔥

Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding.

A composable agent runtime — pair any frontend with any agent backend.

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

Schedule-Free Optimization in PyTorch

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

Friendly and concise wrapper over litellm

Cited 83-model x 49-benchmark LLM evaluation matrix with 18 matrix completion methods

Distilling Human-Aligned Privacy Sensitivity Assessment from Large Language Models

xLM is a modular, research-friendly framework for developing and comparing non-autoregressive language models. Built on PyTorch and PyTorch Lightning, with Hydra for configuration management, XLM m…

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).