projects
software, datasets, models, books, and public research built across more than two decades. featured work leads; the full archive remains searchable.
complete archive · 2001–2026
browse
the project archive
featured work leads by default
- 2025softwarefeatured
Glaurung
An active reverse-engineering framework with a Rust analysis core, Python API, persistent project databases, and optional agent-assisted workflows. One of the top deterministic decompilers on the DecBench sample set.
#reverse-engineering#binary-analysis#rust#python+1 - 2026researchfeatured
Axeyum
A proof-carrying Rust reasoning stack that combines solver search with small independent checkers and explicit unknown results
#formal-verification#smt#rust#webassembly+1 - 2026bookfeatured
Instruction Sets, Programs, and Proofs
A 553-page foundations textbook and evidence ledger for reasoning about instruction-set semantics, equivalence, and optimization
#computer-architecture#formal-methods#risc-v#x86-64+1 - 2026softwarefeatured
Servery
A zero-dependency, batteries-included pure-Python HTTP file server with rich listings, uploads, authentication, TLS, and modern protocol support
#python#http#webdav#tls+1 - 2026modelfeatured
MimeLens
Position-agnostic binary content classifiers and a reference training stack for identifying file types from fragments, packets, and random offsets
#machine-learning#binary-analysis#pytorch#rust+1 - 2024datasetfeatured
FOLIO - Federated Open Legal Information Ontology
Open-source legal data standard containing 18,000+ standardized legal concepts with multilingual support for improved legal industry interoperability
#knowledge-representation#legal-informatics - 2026softwarefeatured
Kernel Lore MCP
An MCP and REST search server for Linux kernel mailing-list archives with transparent corpus coverage and local indexing
#linux-kernel#mcp#information-retrieval#rust+1 - 2025datasetfeatured
Binary-30K Dataset
The first heterogeneous binary analysis dataset for deep learning research, featuring 30,000 diverse executables spanning multiple platforms, architectures, and file formats
#machine-learning#binary-analysis#malware-detection#deep-learning+1 - 2025softwarefeatured
CharBoundary
Character-based text boundary detection for legal documents using Random Forest classifiers, achieving balanced precision-recall with F1 score of 0.782
#natural-language-processing#legal-informatics - 2026bookfeatured
Agentic AI in Law and Finance: Navigating a New Era of Autonomous Systems
A 256-page open-source textbook on autonomous systems, technical architecture, and governance in legal and financial services
#artificial-intelligence#large-language-models#legal-informatics#finance+1 - 2026bookfeatured
The Math Inside the Machine: How Intelligence Emerges from Eleven Simple Operations
A pop-science book explaining that the math inside ChatGPT is the same math you learned between kindergarten and calculus
#artificial-intelligence#large-language-models#mathematics#transformers+1 - 2025softwarefeatured
Binary BPE Tokenizers
Cross-platform Byte Pair Encoding tokenizers for binary executables, enabling 2-3× more efficient transformer-based binary analysis across ELF, PE, Mach-O, and APK formats
#machine-learning#binary-analysis#natural-language-processing#malware-detection - 2025softwarefeatured
IOCTLance
Windows driver vulnerability detection through symbolic execution and taint analysis
#security#symbolic-execution#static-analysis#windows-kernel - 2024modelfeatured
KL3M Toxicity Research
Comprehensive research examining toxicity and bias in legal language models, demonstrating KL3M's superior safety profile through rigorous testing
#ai-ethics#legal-informatics - 2018softwarefeatured
OpenEDGAR
Open source Python client for SEC EDGAR data access and analysis
#financial-technology - 2017datasetfeatured
Law on the Market
A comprehensive 15-year study examining how Supreme Court decisions impact stock market returns, finding significant abnormal returns in 37% of cases
#legal-analytics#financial-analysis - 2026datasetfeatured
OpenMPSC Data
Open dataset of Michigan Public Service Commission regulatory proceedings, 1987–2026, with a public REST API at openmpsc.com
#legal-informatics - 2026datasetfeatured
linux-drivers.com
Evidence-backed dossiers for 864 Linux kernel drivers, recommending which legacy drivers to keep, annotate, deprecate, or remove
#linux-kernel#static-analysis#codex#json-schema+1 - 2026softwarefeatured
Parallel Iliad: Brainrot Edition
A parallel Greek-English reader of Homer's Iliad (Palles 1904/1917) with AI-generated 'brainrot' translations, margin notes, and a searchable character bible
#ai-translation#classical-studies#gpt-5.4#alpine.js+1 - 2026bookfeatured
This Is Server Country: AI, Power, and the Remaking of Rural America
A 402-page investigation into America's trillion-dollar AI data center buildout and its impact on rural communities
#ai-infrastructure#data-centers#energy-policy#power-grid+1 - 2025softwarefeatured
OpenGloss
A synthetic encyclopedic dictionary and semantic knowledge graph for English with 537K sense definitions, 9.1M semantic edges, and 60M words of encyclopedic content
#natural-language-processing#knowledge-graphs#rust#lexicography - 2024softwarefeatured
KL3M Tokenizers
Domain-specific BPE tokenizers for legal, financial, and governmental text, achieving 9-17% efficiency improvements over GPT-4 and LLaMA3
#natural-language-processing - 2018softwarefeatured
LexNLP
Natural language processing and information extraction for legal and regulatory text
#natural-language-processing#legal-informatics - 2016modelfeatured
SCOTUS Predict v2
An enhanced Supreme Court prediction model achieving 70.2% accuracy across 200 years of decisions (1816-2015), analyzing over 240,000 justice votes
#legal-analytics#machine-learning - 2026datasetfeatured
SHELF
A synthetic harness for bibliographic benchmarking, with 62,899 model-written documents labelled with Library of Congress vocabularies and tasks for classification, clustering, retrieval, and pair classification
#machine-learning#natural-language-processing#text-embeddings#benchmarks+2 - 2026datasetfeatured
Michigan Energy Infrastructure & Population Density Map
Multi-layer geospatial visualization of Michigan's energy infrastructure overlaid on Census population density, with a data center siting score for all 1,580 county subdivisions
#geospatial#energy-infrastructure#data-centers#census-demographics+2 - 2026datasetfeatured
Moratorium Nation
A living open dataset tracking 533 local infrastructure moratorium instruments across 42 states, with a companion 50-state legal survey
#data-centers#renewable-energy#battery-storage#zoning+2 - 2025datasetfeatured
KL3M Dataset
Copyright-clean training resources for large language models
#legal-informatics - 2025softwarefeatured
NUPunkt
High-precision sentence boundary detection for legal text
#natural-language-processing#legal-informatics - 2024datasetfeatured
KL3M Data Project
Large-scale copyright-clean dataset containing 132M+ documents and trillions of tokens for training legal language models
#legal-informatics - 2014modelfeatured
SCOTUS Predict
A machine learning model that predicts Supreme Court voting behavior with 70% accuracy, analyzing 60 years of decisions from 1953-2013
#legal-analytics#machine-learning - 2004software
phpDesktop
Web-based personal organization suite predating Google Calendar and Trello by several years
#php#web#javascript#css - 2001software
db-xml
PHP 3.x/4.x library for serialization and deserialization between MySQL/PostgreSQL and XML
#php#mysql#postgresql#xml - 2003software
PHP JAMA
PHP 4.x port of the Java Matrix package for linear algebra computations
#php#linear-algebra#mathematics - 2003software
pystats
Python statistics library built on numarray in the pre-NumPy and SciPy era
#python#numarray#statistics - 2005software
bluebus.be
University of Michigan bus tracking system running on original Google Maps from a dorm room server
#web#javascript#google-maps-api#php - 2002software
mysqlfuck.c
MySQL vulnerability exploit demonstrating default configuration flaws in 2002
#c#security#mysql - 2025software
claude-interceptors
command interceptors that teach ai agents and developers about modern python tooling
#bash#python-tooling#developer-experience#ai-training - 2025software
pyenvsearch
python package exploration for ai agents that stops them from hallucinating apis
#python#cli-tools#ai-agents#llm-integration - 2025software
quick-claude
modular ai agent configuration system that eliminates repeated instructions and ensures consistent behavior across coding sessions
#python#bash#ai-agents#developer-experience+1 - 2026education
RadioCert
Privacy-first self-study courseware for FCC amateur radio licenses and the FAA remote pilot certificate
#education#amateur-radio#aviation#knowledge-graphs+1 - 2026software
Celatim
Typed Python library for authenticated file transfer and reproducible measurement of covert channels in unused, reserved, and optional IETF protocol fields
#network-security#privacy#steganography#network-measurement - 2026research
ChunkLoris
A cross-ecosystem measurement study and replication harness for per-chunk HTTP request amplification in production servers
#http#application-security#performance-measurement#docker+1 - 2026software
Autokernel
An LLM-assisted minimal Linux kernel builder that probes a host, proposes bounded Kconfig changes, builds packages, and boot-tests the result
#linux-kernel#kconfig#python#llm+1 - 2026software
Shuflr
A Rust data-streaming tool for deterministic shuffling of large JSONL corpora without loading the dataset into memory
#rust#machine-learning#jsonl#zstandard+1 - 2025model
Legal Sentence Boundary Detection Paper
Research presenting NUPunkt and CharBoundary libraries for high-precision sentence segmentation in legal text, achieving 29-32% improvement over general-purpose tools
#natural-language-processing#legal-informatics - 2025software
USBills.ai
Open-source platform using AI and NLP to make US federal legislation accessible through plain language summaries, ELI5 explanations, and readability metrics
#legal-informatics#natural-language-processing - 2024dataset
Federal Bill Statistics
Original source code and data infrastructure that powered the initial version of usbills.ai platform
#legal-informatics - 2024model
Linux as a Model
Training transformer models to memorize Linux kernel source code to demonstrate issues with AI training data licensing
#machine-learning#open-source - 2024model
KL3M Model Research
Research and development repository for advancing the Kelvin Legal Large Language Model family with new architectures and training approaches
#machine-learning#legal-informatics - 2024model
All the Patents
Generating and publishing obvious inventions using AI to challenge the patent system
#machine-learning#patent-law#legal-informatics - 2024software
ALEA Preprocess
High-performance data preprocessing library for large language model training, supporting pretraining, SFT, and DPO datasets with Rust-powered efficiency
#machine-learning - 2024software
FOLIO Data Generator
Python library for generating synthetic legal data using the FOLIO knowledge graph, supporting both procedural templates and LLM-based generation
#legal-informatics - 2024software
FOLIO API
Public RESTful API for the Federated Open Legal Information Ontology, providing programmatic access to 18,000+ legal concepts with multiple output formats
#legal-informatics - 2024software
FOLIO Python Client
Python library for interacting with the Federated Open Legal Information Ontology, providing search, exploration, and format conversion capabilities
#knowledge-representation#legal-informatics - 2023model
GPT-4 Passes the Bar Exam
Research demonstrating GPT-4's ability to pass the Uniform Bar Examination, significantly outperforming both human test-takers and prior AI models
#ai-evaluation#legal-informatics - 2023software
leeky
Training data contamination detection library for black-box language models, implementing six testing methods to identify potential data leakage
#ai-ethics#machine-learning - 2023model
GPT as Knowledge Worker
Research evaluating GPT models' capabilities on the Uniform CPA Examination, exploring AI's potential to transform knowledge work
#ai-evaluation - 2023model
GPT Takes the CPA Exam
Initial repository for research evaluating GPT models on the CPA exam, later developed into the comprehensive "GPT as Knowledge Worker" project
#ai-evaluation - 2022model
GPT Takes the Bar Exam
Groundbreaking research demonstrating GPT-3.5's performance on the Multistate Bar Examination, predicting AI's ability to pass professional legal licensing exams
#ai-evaluation#legal-informatics - 2022model
FMLGen
A humorous AI project that generates absurd "F*** My Life" stories using modern language models, comparing current capabilities to 2013 n-gram approaches
#natural-language-processing - 2022software
rfcorr
Python library for Random Forest-based correlation measures, providing alternative approaches to traditional correlation analysis using tree-based ensemble methods
#machine-learning - 2018software
pyghcn
Python 3 library for accessing and analyzing NOAA Global Historical Climatology Network (GHCN) weather and climate data
#climate-science - 2018software
amos3
Python 3 client for the Archive of Many Outdoor Scenes (AMOS), enabling access to billions of outdoor webcam images for computer vision and environmental research
#computer-vision - 2017dataset
Measuring and Modeling the U.S. Regulatory Ecosystem
Large-scale empirical analysis of regulatory complexity using 165,000+ SEC filings to map the evolution of the U.S. regulatory landscape
#computational-law#complex-systems - 2015software
Complex Systems 530 - Winter 2016
Course materials for "Computer Modeling of Complex Systems" at University of Michigan, teaching agent-based modeling and computational approaches to complex systems
#complex-systems#educational-technology - 2015dataset
The Race to the Bund
An innovative analysis of European financial integration using eigendecomposition of sovereign bond yield correlations from 1872 to 2010
#financial-analysis - 2014software
Complex Systems 530 - Winter 2015
First iteration of "Computer Modeling of Complex Systems" course at University of Michigan, establishing foundation for computational complex systems education
#complex-systems#educational-technology - 2014software
Well-Settled Research
A computational legal research project analyzing Supreme Court decisions and legal precedents using natural language processing
#legal-analytics - 2013dataset
U.S. Code Complexity
Computational analysis measuring the complexity of the United States Code using mathematical and network science approaches
#computational-law#complex-systems
no projects match those filters.
try a broader search or reset the archive.