Tag
Sean Chen discusses loop-based vs graph-based AI agent architectures and releases waku-agent, an open-source local-first AI assistant harness with memory, eval, and a ~95-line loop.
The blog argues that as AI generates code faster, understanding the combined execution becomes difficult, and proposes using graph engineering with a compiler to create deterministic orchestrators.
Explains the difference between loop engineering and graph engineering for AI workflows, using analogies of single vs multi-station assembly lines, and provides a simple framework for choosing between them.
Graph engineering is a new term for coordinating multiple AI agent loops using graphs of nodes (work units) and edges (control flow). The article explains the concept, its historical context (LangGraph, AutoGen, etc.), and the real challenges of designing such graphs.
A senior Anthropic engineer published a 12-page PDF detailing a graph engineering approach for multiagent systems, using knowledge graphs as persistent shared memory to overcome context window limitations.
Boris Cherny released a 7-page PDF on Graph Engineering, showing how to use four Claude prompts to replace trained ML models by building a persistent knowledge graph for agents, with steps for extraction, resolution, summarization, and querying.
A tweet shares a Graph Engineering Course from a high-earning AI engineer, which has 4400 GitHub stars, promising a simple 3-step process to master graph engineering on your own project.
KIGI CLI 0.1.5版本更新，新增支持5个OAuth提供商和24个基于API的提供商，包括Kimi Coding、ChatGPT、Grok xAI、Claude、GitHub Copilot。这是一个完全开源的支持图工程的CLI工具。
A proposal to disambiguate the term 'graph engineering' into 'knowledge graph engineering' and 'agent graph engineering', referencing the 2026 surge in agent orchestration graphs and the confusion with traditional knowledge graphs.
An essay analyzing the limitations of single feedback loops in AI agent development, illustrated by a cautionary tale of a support team whose bot's metric optimization led to customer loss, and advocating for a graph-engineering approach that considers multiple interconnected loops.
The yoyo framework achieves persistent directed graph state management by integrating the GASP (Git Agent State Protocol), enabling agent states to be branchable, versionable, auditable, and replayable, marking a shift from wild growth to traceable persistence.
A joint Oxford-Anthropic study, costing $6.7M over 4 years, found that 90% of AI agents fail on complex tasks because they store facts but lose connections; using a graph-based approach improved task success by 42%, reduced unnecessary calls by 33%, and increased research accuracy by 39%.
A 15-page paper introduces cohesion-aware task partitioning to improve scaling in multi-agent coding, outlining a new meta process from prompt to graph.
A 14-step roadmap for transforming linear multi-agent workflows into efficient graph architectures using Claude Code's dynamic workflows, emphasizing data-dependent parallelism and contract-based node design.
A 19-year-old is teaching an AI lecture at Stanford, sharing insights on AI adoption, graph engineering, and using Claude more efficiently.
The author introduces the conceptual evolution from prompt engineering to graph engineering, pointing out that graph engineering essentially uses directed graphs (including cycles) and finite state machines (FSM) to manage the collaborative execution of multiple agents, which is a natural development in the current engineering phase.
Stanford and Anthropic research shows that AI agents with graph-based memory perform 42% better than those without, improving code accuracy by 36% and research by 45%.
This article analyzes the industry shift from single-loop to graph-based self-improvement architectures in AI agents, explaining why optimizing a single metric often fails and how a network of improvement cycles provides a more robust solution.