An open-source toolkit for data valuation and Data Shapley estimation.

A neural-symbolic framework for multimodal analytic geometry problem generation.

A retrieval-augmented generation framework integrating FAIR Digital Objects for semantic analysis.

An agentic routing framework implementing a four-layer routing stack for model selection.

A model editing framework for handling temporal facts in LLMs.

A benchmark for agentic end-to-end code generation with backend services.

Open-source high-performance data profiler with optimized matching dependency discovery.

RLVP

★ 80

An RL post-training framework for multi-PDE solver code generation with continuous physics rewards

An open-source Python package to efficiently detect text containment and copyrighted material in large corpora.

A meta-solver within a robust double-oracle framework for learning approximate PR-MRE strategies via deep RL.

Benchmark for irregular clinical time series QA constructed from ICU records.

RSLoRA

★ 80

A training-free rank allocation framework for LoRA using representational sensitivity probing.

OSCAL

★ 80

Open Security Controls Assessment Language for machine-readable compliance artifacts.

MAGIC

★ 80

A system for transition-aware generation of navigable multi-scene game worlds using LLMs.

SDABench

★ 80

Benchmark for evaluating LLM capabilities in scientific data analysis.

A trace-grounded diagnostic toolkit for evaluating agentic trading systems.

A framework for auditing risk-sensitive decision-making in LLMs using no-limit Texas Hold'em.

Open-source Python library for modeling and discrete-event simulation of supply chain networks.

WinPodX

★ 80

Runs Windows apps from a self-hosted guest and surfaces them as native windows on Linux.

A local-first, open-source personal finance management tool.