Graph-Native Infrastructure for Context and Accountable AI Systems
-
Updated
Aug 16, 2026 - Python
Graph-Native Infrastructure for Context and Accountable AI Systems
PPO x Family DRL Tutorial Course(决策智能入门级公开课:8节课帮你盘清算法理论,理顺代码逻辑,玩转决策AI应用实践 )
BKN Foundry is the back-end foundation of OpenBKN. It transforms ontology-driven business semantics into runtime services: data, logic, actions, security governance, and observability.
Web console for OpenBKN — build, manage, and collaborate on business knowledge networks. React + TypeScript frontend for the platform's admin UIs and workspaces.
Simpack Pro 2.0: AI Investment Intelligence Platform 2026
This repo illustrates how to combine LLMs and rule-based services to generate answers grounded on business policies
A neuro-symbolic runtime architecture (DIR) for Responsibility-Oriented Agents (ROA). By decoupling probabilistic LLM reasoning (User Space) from deterministic execution (Kernel Space), it ensures safe, invariant-driven, and auditable AI autonomy.
A modern, enterprise-ready business intelligence web application. Unleash the value of your data. 📈 📉 📊
A deep exploration of AI-driven foresight, how predictive models evolve into strategic collaborators. This repository presents Forecasting the Future of Forecasting, a professional essay on reflexive intelligence, human–AI collaboration, and the design of adaptive, explainable forecasting systems.
A deep exploration of loyalty as a multi-dimensional behavioral system shaped by intent, habit, and sensitivity. This article introduces a geometric framework for modeling customer behavior, predicting churn trajectories, and designing ML systems that understand loyalty as a dynamic state, not a metric.
Deterministic decision-intelligence MCP server for AI agents — 17 tools (bandits/LinUCB, HiGHS LP/MIP, PageRank, Monte Carlo, CMA-ES, conformal). Sub-25ms. Zero LLM cost. 11 free, no key. Listed on the MCP Registry & Glama.
End-to-end logistics decision engine combining demand forecasting, simulation, and optimization to support data-driven planning under uncertainty.
Queryable reasoning memory for AI agents. Six typed queries (why, tensions, blocked, whatIf, alternatives, counterfactual) over reasoning graphs. Vector stores remember what. FlowScript remembers why. TypeScript SDK + MCP server.
Production-ready Claude Code decision intelligence marketplace with adversarial routing, evidence-driven analysis, specialized agents, benchmarks, and automated validation.
IntelliSphere is an Enterprise Decision Intelligence Platform built with Spring Boot, React, and PostgreSQL. Powered by Gemini AI, it analyzes multi-industry telemetry, models operational risks (Agriculture, Smart Cities, Healthcare, Manufacturing), and compiles automated analytical PDF reports.
OPC(一人公司)每日决策情报 — AI-powered decision intelligence for one-person companies
Enterprise Decision Intelligence System — a real-time, AI-powered platform that ingests cross-system enterprise data, detects anomalies, finds root causes, and recommends explainable actions. Python/FastAPI + React + Claude. Grounded AI: the LLM never invents a number.
Compute capital allocation for AI agents — fund only actions whose expected marginal value justifies tokens, cost, latency and risk.
PALABRE is a CLI orchestrator that lets multiple AI agents installed on your machine talk to each other: Claude Code, Codex, OpenCode, Vibe and Ollama.
Add a description, image, and links to the decision-intelligence topic page so that developers can more easily learn about it.
To associate your repository with the decision-intelligence topic, visit your repo's landing page and select "manage topics."