Framework providing deterministic replay and content-addressable caching for workflows

An eBPF-first observability platform using a BYOC architecture for cloud-native environments.

A benchmark and methodology for handling class imbalance in conformal prediction.

Multimodal framework integrating image analysis and osteometric measurements for bird bone identification.

A transformer-based model for classification through in-context learning on tabular data.

Implementation of Collaborative Weighting Actor-Critic for off-policy reinforcement learning.

A multi-agent framework for event-centric explainability in cybersecurity investigations.

Go/WASM implementation for simulating network congestion in the browser

An urban data science benchmark for evaluating AI agents in urban scenarios.

Docker stack manager for compose files.

A framework for tokenization, authentication, and acceptance of AI-driven agent transactions.

CLI tool to switch Claude Code accounts without re-logging

A tool for artifact-driven investigation of NTFS file systems.

Native iOS application for the RomM game library

SteamOS downloader and syncer for RomM

A Tmux TUI for running Claude Code, Codex, and OpenCode.

A design probe for prototyping and evaluating agent UX approaches in a browser.

A framework for simulating human responses to policy interventions using LLMs.

A value-aware memory management system with interactive analytics for LLM-based agents.

Anchored-and-Agile Test-Time Adaptation framework for evolving traffic sensor networks.