Model-independent sketch-to-image studies: seed scouting, controlled variation, replayable manifests, and a zero-download local tour.
Production-grade TypeScript AI runtime focused on reliability, governance, and reproducible LLM systems. Multi-provider gateway, agents, RAG, workflows, policy engine, audit trails, and deterministic testing — built for teams shipping AI in production.
A modular, self-contained file format for executable AI prompts, logic, and data.
Deterministic factual substrate for multi-agent AI. Shared evidence-backed facts and reproducible grounding through dataset_hash.
Holistic Multimodel Domain Analysis: A New Paradigm for Robust, Transparent, And Reliable Exploratory Machine Learning that Considers Cross-Model Variability in Feature Importance Assessment
Protected v1.0.0 baseline for ARC-Neuron LLMBuilder — local-first LLM lifecycle tooling for benchmark receipts, candidate promotion, lineage, and governed model improvement.
A reproducible Docker-based pipeline for running machine learning experiments with GPU support. This repository provides pre-configured Docker images, environment files, and scripts for: - Setting up GPU-enabled containers - Running training and inference - Managing environments reproducibly
The evidence layer for AI systems and agents - reproducible evaluation, verification, regression and release evidence.
Git-like branching, deterministic replay, and evidence-driven evaluation for reproducible AI agents.
A moment-selected symbolic field for AI with auditable draws, Dreamspell context, 671 symbolic coordinates, and live Thinking 3/6/9.
Deterministic record and replay for agent model calls, tools, files, approvals, clocks, and random values.
Native llama.cpp orchestration for quantized LLM evaluation, drift analysis, and reproducible model comparison.
Open-source capability foundry for turning complex AI behavior into small, testable, local, and rebuildable systems.
Reliable-AI engineering portfolio spanning agent security, evaluation, replay, energy, climate, and product systems.
Turn any Git repository into a local SWE-bench-style coding-agent benchmark.
Personal GitHub profile of Zihang Zhou.
To associate your repository with the reproducible-ai topic, visit your repo's landing page and select "manage topics."