Tagged articles

code graph

8 articles · Page 1 of 1

Oct 15, 2026 · Artificial Intelligence

7-Layer Architecture for AI-Native SDLC: How Anthropic, OpenAI, GitHub & Kiro Map to the Stack

This article presents a 7-layer reference architecture for AI-native software development platforms, mapping capabilities from Anthropic, OpenAI, GitHub, and AWS Kiro across infrastructure, specifications, context engineering, agent orchestration, evaluation, production feedback, and governance layers, with a practical migration path from traditional DevOps.

7-layer architectureAI-Native SDLCDevOps migration

0 likes · 19 min read

7-Layer Architecture for AI-Native SDLC: How Anthropic, OpenAI, GitHub & Kiro Map to the Stack

ITPUB

Sep 28, 2026 · Artificial Intelligence

How We Cut Token Costs 50% in a Multi-Agent Harness Workflow

A team reduced token costs 50–65% in a 1-TL + 6-sub-agent Harness workflow by applying three principles—load only needed context, eliminate irrelevant context, remove duplicate context—through ten techniques including progressive disclosure, code graphs, CLI over MCP, and parallel tool calls, measured via AgentLens.

AgentLensHarness workflowLLM cost reduction

0 likes · 23 min read

How We Cut Token Costs 50% in a Multi-Agent Harness Workflow

Geek Labs

Sep 14, 2026 · Artificial Intelligence

Stronger AI Coding Agents Burn More Tokens: How roam-code's Code Graph Cuts Costs 63%

roam-code builds a local SQLite code graph using tree-sitter for 28 languages, letting AI agents query precise call relationships instead of grep or RAG, reducing agent turns by 83%, tokens by 80%, and cost by 63% in experiments, while adding deterministic pre-edit context injection and post-edit verification gates.

AI coding agentsMCPSQLite

0 likes · 16 min read

Stronger AI Coding Agents Burn More Tokens: How roam-code's Code Graph Cuts Costs 63%

JD Cloud Developers

Jul 22, 2026 · Cloud Native

How AI Quickly Reads Your Codebase: Three Evolutions of Joy-Code-Graph Cloud Service

The article explains how Joy-Code-Graph transforms AI code assistants from blind guesswork into globally aware tools by deploying a self‑hosted, cloud‑native code graph service that integrates directly with Joygen, offers zero‑install sandbox access, and persistently stores the graph in a dedicated repository branch.

AI programmingJoygen integrationMCP

0 likes · 10 min read

How AI Quickly Reads Your Codebase: Three Evolutions of Joy-Code-Graph Cloud Service

Su San Talks Tech

Jul 18, 2026 · Artificial Intelligence

Why CodeGraph Is Suddenly Going Viral

CodeGraph, a local‑first code intelligence tool for AI programming assistants, builds a searchable knowledge graph with tree‑sitter and SQLite, cutting tool calls by 71%, token usage by 57% and task time by 46% while keeping data private and requiring only a few minutes to install and use.

AI programmingCLICodeGraph

0 likes · 16 min read

Black & White Path

Jul 12, 2026 · Information Security

Local Vulnerability Research Pipeline: 14B Code Model Powers Automated Exploit Mining

The local‑vuln‑research‑pipeline, built around the 14B Qwen2.5‑Coder model, combines a deterministic code‑graph with LLM‑driven exploitability reasoning to exhaustively enumerate source‑to‑sink paths across multiple languages, offering detailed reports while running entirely on local hardware.

LLM auditingQwen2.5-Codercode graph

0 likes · 9 min read

Local Vulnerability Research Pipeline: 14B Code Model Powers Automated Exploit Mining

Alibaba Cloud Developer

Mar 19, 2026 · Artificial Intelligence

How Engineering Knowledge Engines Turn AI Coders into Reliable Collaborators

The article analyzes the limitations of current AI coding agents—narrow perception, fragmented knowledge, and missing high‑dimensional context—and presents an Engineering Knowledge Engine that integrates vector retrieval, code and commit graphs, RepoWiki, memory, and Agentic Search to provide structured, evolving context, dramatically improving task success, token efficiency, and code quality.

AIAgentic SearchKnowledge Engine

0 likes · 11 min read

How Engineering Knowledge Engines Turn AI Coders into Reliable Collaborators

PaperAgent

Dec 9, 2025 · Artificial Intelligence

How Code Graph Model (CGM) Redefines Repository‑Level Code Understanding

The Code Graph Model (CGM) introduced by Ant's multimodal code team integrates repository‑level graph structures into open‑source LLMs, achieving a 44% solve rate on SWE‑bench Lite, eliminating agent dependence, and demonstrating a novel graph‑enhanced code model through multi‑granular graph construction, dual‑modal alignment, and a lightweight GraphRAG framework.

AIGraphRAGLLM

0 likes · 9 min read

How Code Graph Model (CGM) Redefines Repository‑Level Code Understanding