ai-transparency

The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas and agent harnesses powering today's AI products. Captured with OrcaReplay.

An open standard for declaring AI usage in software projects.

1,017 system prompts from real AI products, audited span by span against the eight AISPA assurance dimensions

TRACE protocol for auditing decision-provenance in AI-assisted scientific workflows

Test what AI watermark and provenance evidence exists, whether it verifies, and what survives publishing.

Evidence cards for narrow public AI, ML and data claims: frozen protocol, hashed sources, honest result status.

The LLM Unlearning repository is an open-source project dedicated to the concept of unlearning in Large Language Models (LLMs). It aims to address concerns about data privacy and ethical AI by exploring and implementing unlearning techniques that allow models to forget unwanted or sensitive data. This ensures that AI models comply with privacy.

SBOM generation for Python & AI projects. Native Hatchling build-hook. Extract metadata from GGUF, ONNX, and PyTorch models. Build SBOM directly from Hugging Face URL.

Embed, extract and verify C2PA Content Credentials in plain Unicode text.

Crovia substrate — the 2026 archive: autonomous collectors, Ed25519-signed observation envelopes, batch Merkle seals, OpenTimestamps anchors, Phase-0 truth post-processors. Superseded for live observation by TACET (croviatrust/countersign).

Indice d'implication de l'intelligence artificielle

Code for the paper "ClipMind: A Framework for Auditing Short-Format Video Recommendations Using Multimodal AI Models"

A study piece on AI ethics, safety, and emergence - principles, HR for human-AI teams, technical guardrails, and philosophy for working with possibly-emergent AI. Co-authored by Richard Bland (human) and Serene [AI].

The cognitive discipline your AI-assisted projects need. Framework + Rust CLI to externalize scope, decisions, and risks (Charters, AILOG, AIDEC, ADR) so AI agents stay coherent across many turns. ISO 42001 / EU AI Act / NIST AI RMF evidence as a side effect. EN/ES/zh-CN.

A small, docs-first workflow for AI-assisted research that keeps claims, sources, uncertainty, review findings and human decisions inspectable.

An independent, open vocabulary for declaring generative AI use, human contribution and review.

🛠️ Log and trace your AI's decisions securely with DecisionTrace, ensuring transparency and integrity in every choice it makes.

Scores political events on constitutional impact vs media coverage. 59+ weeks of immutable public data.

OKI TRACE: Local LLM observability. See step-by-step, layer-by-layer what your AI thinks. Logit Lens & Attention for HuggingFace models.

VoicePrint: Forensic speaker attribution for AI voice blends. Match synthetic clones to source voices via speaker embeddings & cosine similarity. Open-source Python research toolbox.