Show GN: $300/월 AI 비용을 절반으로 줄인 OSS — claude-ns-hub
Context Compression과 Decision Memory를 통한 AI 토큰 비용 50% 절감
Context Compression과 Decision Memory를 통한 AI 토큰 비용 50% 절감
Your LLM Bill Is Exploding Because of Architecture, Not Pricing -- Here's the Fix
R@5 95.2% 달성 및 토큰 92% 절감을 구현한 4-Tier AI 영구 메모리 시스템
Designing a Multi-Agent System for Engineering Support at Scale: A Case Study From Grab
Building a Biomedical GraphRAG Inference System: Comparing LLM-Only, Basic RAG, and GraphRAG Pipelines
From Rigidity to Explicitness: How AI Changes the Role of Constraints in Software
LLM Foundry finally stops being a toy and starts acting like a system
Building an AI Agent Harness from Scratch: The Architecture Between LLM and Agent
🏗️ Building High-Quality AI Agents 🤖 — A Comprehensive, Actionable Field Guide 📘
Context Compression in .NET
memo-agent is a terminal-based AI assistant application (Hermes Agent simplified version), built with TypeScript + React + Ink. features persistent memory, MCP tool extensions, and intelligent context compression. https://github.com/lxfu1/memo-agent
43개 내장 도구와 Swarm Coordination을 통합한 경량 LLM 에이전트 인프라
Context Windows Explained: Why 1M Tokens Changes How You Architect AI Applications
Agent Development Kit 2.0, ADK-java 1,1 et Go 1.0 🚀
Plug-and-Play Context Compression for Any LLM API — CRISP