graph-engineering

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

An open-source graph engineering runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes.

[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Agents & Agentic Graph Engineering).

agent wiki +engineering skills

Build stateful agent workflows with typed outputs, reusable tools, session forks, and ordinary TypeScript.

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

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown library (loop-graph), not a framework.

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

Desktop app for harness engineering, loop engineering, graph engineering—and whatever comes next in local AI-agent workflows.

🕸️ 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.

Copy-paste prompts that turn your AI agents from a waiting line into a graph: a 5-min demo, false-edge audit, diamond research, adversarial review, consultant roundtable, and an issue tree that dispatches itself. EN + 繁中.

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

Graph Engineering for Agent Skills: a specification and toolchain for dynamically discovering context and building observable, testable, and recoverable agent workflows.

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

Interactive GitHub issue dependency DAG and issue explorer

Turn any multi-step process into a guarded graph a machine can actually execute — typed nodes, total exit guards, bounded retry loops, durable run state, and a ledger of every step that could not run. A Claude Code plugin.

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。

Progress-aware execution for durable, grounded, token-efficient coding agents.

Claude Code skill: design multi-agent workflows as dependency graphs, not linear pipelines