The deterministic context engineering platform for open source AI. Connect open models and ontologies with context graph harnesses to build explainable, reliable agents.

Turns repeatable, domain-agnostic workflows into multi-step graph-driven loops.

An end to end implementation of Graph Engineering as proposed by Andrew NG and Peter Steinberger

🕸️ Engineer the organization, not just the agent. 561 curated resources · 9 design layers · 11 sections · 250 papers & preprints — a field guide, CC0 open dataset, and interactive atlas for graph-structured multi-agent systems: roles, topologies, handoffs, work graphs, state, gates, reliability, observability.

Design grounded graphs of governed improvement loops.

Installable graph engineering for Claude Code, Codex, OpenCode, and Cursor — dependency-graph execution with local caching, quality gates, selective retries, and live reports

A production-grade Python & Streamlit reference implementation of the 5-Layer Graph Engineering Taxonomy, implementing the complete technical outline

DyroEngineeringFlow 是面向多仓团队的本地优先工程自动化与交付控制平台。它将开发线、Git worktree、任务编排、 Agent 启动、质量门禁、独立复核与合并审计统一到可版本化配置中，帮助团队从任务创建到交付合并形成清晰、安全、 可追溯的自动化流程。日常通过简洁命令 dyro 即可完成初始化、环境检查、任务执行与协作交付。

An incident response copilot built with LangGraph, parallel investigation, human-in-the-loop approval, and long-term memory that improves with each resolved incident.

Codex skill for adaptive development workflows with executable JSON graphs and SVG previews

The coding-agent workbench where a deterministic scheduler — not the model — owns control flow. Orchestrates Claude Code & Codex through one auditable, resumable control plane.

Python toolkit for multi-step AI/agent systems as explicit graphs — define nodes/edges, structural validate (V1–V9), Mermaid visualize, pattern init, and skeleton walk. Vendor-agnostic. Runtime agent execute later.

A field guide to wiring AI agents as graphs — patterns, runnable code, and the token and latency costs nobody names

Design the structures your agents work through — knowledge graphs for memory, task graphs for orchestration. Playbook + agent skill + runnable stdlib-only pipeline.

A Codex Agent Skill for designing governed, project-local agent graphs.

Superpowers plugin as graph-engineering.

Graph engineering and multi-agent orchestration skills for Claude Code, Codex, and other AI coding agents.

基于 Graph Engineering 的中文长篇 AI 创作系统：持久化 State、人工 Gate、受控 Loop 与叙事连续性校验。

Contract-gated verification for multi-agent research pipelines. Validates every artifact, walks the provenance hash chain, checks the reviewer was not the producer, and returns an exit code. Orchestrates nothing, calls no model API.

Build graph-structured multi-agent systems with this collection of research papers, datasets, and design patterns for programmable AI organizations.