transparent-ai 开源项目推荐（21 个）

ttguy0707 /CyberClaw

下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 全行为审计 | 两段式安全调用 | 双水位记忆 | 心跳任务 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

rabia174 /ConformaSight

Conformal Prediction-Based Global and Model Agnostic Explainability for Classification tasks.

AmirhosseinHonardoust /Financial-Fraud-Risk-Engine

A complete end-to-end fraud detection system for financial transactions, featuring data pipelines, cost-sensitive ML modeling, explainability with SHAP, threshold optimization, batch scoring, and an interactive Streamlit dashboard. Designed to simulate real-world fintech fraud-risk workflows.

iiishop /StratumCode

AI coding agent that shows its work — every step visible, every patch approved by you. Build projects brick by brick, stay in control.

AmirhosseinHonardoust /Pricing-Negotiation-Intelligence

This article reframes pricing as a negotiation rather than a prediction, showing how price emerges from tensions between product reality, market dynamics, and buyer behavior. It introduces negotiation-aware ML, value decomposition, and equilibrium modeling to build transparent, human-aligned pricing systems.

AmirhosseinHonardoust /Car-Value-Decomposition-Theory

This article explores the theory behind explainable car pricing using value decomposition, showing how machine learning models can break a predicted price into intuitive components such as brand premium, age depreciation, mileage influence, condition effects, and transmission or fuel-type adjustments.

Pro-GenAI /LML-DAP

📊 Language Model Learning a Dataset for Data-Augmented Prediction

alexrodic /Conscience-by-Design

The Conscience Layer Prototype, created by Aleksandar Rodić in 2025, establishes a research foundation for ethical artificial intelligence. It brings moral awareness into computation through principles of truth, human autonomy, and societal responsibility, defining a transparent and accountable form of intelligence.

haghish /HMDA

Holistic Multimodel Domain Analysis: A New Paradigm for Robust, Transparent, And Reliable Exploratory Machine Learning that Considers Cross-Model Variability in Feature Importance Assessment

changsheng137 /information-sphere

🌐 Information-Oriented Sphere System: From Data to Information Paradigm Shift | 信息导向球面系统 - Lossless reconstruction (MSE=0), Full interpretability, 2.28x optimized

timosaarinen /promptly

Git-native desktop tool for crafting context-aware LLM prompts from local codebases with full transparency and control

arenagroove /augmented-intelligence-toolkit

Modular prompt system for transparent, multi-perspective, non-human AI reasoning.

Atharv-B /What-is-my-robot-thinking

Accompanying code for IROS 2026 paper - What Is My Robot Thinking? Design Considerations for Transparent and Trustworthy Shared Autonomy

lonecat1 /seenagent

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

MarianoMosquera /marianomosquera.github.io

Repositorio académico sobre ética institucional, transparencia, gobernanza y rendición de cuentas. Ontologías, investigación y herramientas de análisis y deliberación asistidas por inteligencia artificial.

RohitSheikh /Car-Value-Decomposition-Theory

🚗 Decode car values using a transparent machine learning system that enhances price understanding through explainable methods.

algoq369 /life

Conceptual Intelligence System - Building genuine intelligence through concepts, not neural networks

Ridhwanlai /COGS300-Perceptron

This is a fully physical implementation of a foundational machine learning model: the perceptron. Built as a final project for COGS300 at UBC, this work transforms an abstract mathematical concept into a tangible, interactive system you can see, touch, and probe. At its core, the project explores what happens when we remove abstraction from AI.

eknobl /moria-grendel

Moria Grendel - Open-source AI influencer experiment for theaivideocreator.ai

openarsenalspecs /Human-in-the-Loop

Human-centered AI specs focused on auditable, controlled, and transparent systems across governance, orchestration, and civic infrastructure. A Specification Branding License is negotiable for attribution-free deployment, with pricing based on size and scope of implementation.