Notes on how to use the internal language of toposes in algebraic geometry

A clean PyTorch / PyG implementation library of Sheaf Neural Networks as Message Passing comprising all variants and a benchmark suite with 14+ Datasets.

Full spectrum sheaf neural network over arbitrary CW complexes.

Sheaves library for graph abstractions based on NetworkX

From Cybernetics to Categorical Semantics in Distributed Software Organizations — Formalizing Organizational Viability in Open Source Software Governance

My master's thesis in the realm of Graph Neural Networks. In this work we propose a novel way to precompute the sheaf Laplacian motivated by the connection that exists between the global section of a sheaf and the minimization of the Dirichlet energy via graph convolution.

Persistent sheaf cohomology — cellular sheaf Laplacians, Vietoris-Rips complexes, multi-modal data fusion

Open-source data plane primitives: arena storage, schema contracts, filesystem projection, tree-sitter AST, LSP integration

A sheaf theory planner created by LLMs. For research.

Pre-alpha prototype: federated learning by Karcher mean on a symmetry groupoid

GrainVDB: High-performance vector search engine written in native C++ and Metal. Optimized for Apple Silicon Unified Memory and local-first AI applications.

Generalized geometric Langlands via derived-correspondence persistence on the manifold-constrained canonical lane. Reproducible local-to-global theorem package.

A survey of sheaf-theoretic algorithms — Neural Sheaf Diffusion and the sheaf Laplacian — for data scientists and AI researchers in industry.

Geometric Langlands via Hecke-eigensheaf persistence on the manifold-constrained canonical lane. Reproducible local-to-global theorem package.

Sheaf theory and community detection

Exploration des principes mathématiques derrière la frustration géométrique et ses applications en science des matériaux et au-delà.