#cross-session context
194 related articles
·3 min
Memorex Code Open-Sourced: Giving Coding Agents Long-Term Memory
Memorex Code is an open-source long-term memory system for Coding Agents, solving cross-session memory loss. Features auto-recall, deduplication, and local codebase scanning for Cursor, Claude Code, and more.
Read more →
·3 min
Spring AI 2.0 in Practice: A Complete Guide to Building a Code Generation Agent from Scratch
Learn how Spring AI 2.0 natively supports Agent development. Build a code generation assistant by reverse-engineering Claude Code's architecture with Agent Utils, covering task planning, long-term memory, and Tools invocation.
Read more →
·3 min
Spring AI 2.0 in Practice: Building an Enterprise-Grade Code Assistant Agent from Scratch
Deep dive into Spring AI 2.0 core updates. Reverse-engineer Claude Code with Agent Utils to build an enterprise-grade code assistant covering ReAct, Tools, MCP, and long-term memory.
Read more →
·5 min
LLM Reasoning Chains Stolen: Deep Dive into Architecture-Level Vulnerabilities Across Three Major AI Providers
Deep analysis of a security paper revealing architecture-level vulnerabilities in Anthropic, OpenAI, and Google's encrypted reasoning chains, covering decryption jailbreak attacks, distillation theft, privacy leaks, and Agent prompt injection.
Read more →
·5 min
What Is DeepSeek Harness? Dissecting the 7 Core Modules of Agent Architecture
Deep analysis of DeepSeek Harness: not just a product, but an Agent architecture paradigm. Dissecting 7 core modules including tool calling, memory systems, and sandbox environments.
Read more →
·3 min
AT&T's AI Sales Agent: Google Reveals an Enterprise-Grade Deployment Blueprint
Google and AT&T reveal a production AI sales Agent system using persistent memory for cross-channel continuity, achieving line-level hyper-personalization on ADK+Gemini architecture.
Read more →
·5 min
The Complete Guide to Pi Agent: How Four Tools Beat Codex and Claude Code
Deep analysis of Pi programming Agent's minimalist design: just four tools and a 1000-token prompt outperform Codex and Claude Code in speed, cost, and code quality.
Read more →
·2 min
Berd: A Deep Dive into the Open-Source Mac Desktop AI Agent Workspace
Deep dive into Berd—an open-source Mac desktop AI Agent app with project management, skill configuration, multi-model support, and local context access for engineers and builders.
Read more →
·3 min
Claude Code Multi-Session Communication and Collaboration: A Practical Exploration of Multi-Agent Programming
Exploring how multiple Claude Code sessions can communicate and collaborate, enabling multi-agent programming workflows with message-passing mechanisms and AI coordination.
Read more →
·3 min
ChatGPT Computer History Feature Explained: How AI Remembers Your Workflow
OpenAI's Computer History feature for ChatGPT captures interaction events to let AI remember your workflow. Learn how it works, its privacy design, and automation potential.
Read more →
·2 min
Public AI with Shared Memory: What Happens When All Users Share One Brain?
An unconventional AI project lets all users share one memory, sparking debate on privacy, security, and collective intelligence. We analyze its design, risks, and future hybrid architectures.
Read more →
·4 min
DeepSeek-Harness Open-Source Framework Explained: An Agent Architecture Where Everything Is a Plugin
Deep dive into DeepSeek-Harness open-source agent framework: from Codis kernel to plugin architecture, four preset modes, transparent session logs, and its open-source ecosystem strategy.
Read more →
·3 min
Loop Engineering Explained: From Agent Loops to a New AI Development Paradigm
A deep dive into Loop Engineering, covering Agent Loop think-act mechanisms, the evolution from While loops to Graph structures, and the practical value of this emerging AI development methodology.
Read more →
·3 min
AI-Memory: Building a Cross-Tool Long-Term Memory System for Coding AIs
AI-Memory is a Rust-based open-source project providing long-term memory for Claude Code, Cursor, Aider and other Agent coding CLIs, enabling seamless handoff between vendors.
Read more →
·4 min
Complete Interview Guide: LangChain's Core Features and Six Major Application Scenarios
Deep analysis of LangChain's four core features (unified model interface, modular architecture, agent tool calling, memory management) and six application scenarios (RAG, Agent, chatbots, etc.) for LLM development interviews.
Read more →
·2 min
GitHub Daily · August 16: A Dual Explosion of Localized AI and Edge Intelligence
GitHub Trending Aug 16: Localized AI explodes with unsloth's local training UI, needle's 14MB edge model, and ai-memory solving Agent long-term memory.
Read more →
·4 min
Deep Dive into Claude Code's Memory System: From CLAUDE.md to Auto Memory — The Complete Architecture
Deep analysis of Claude Code's Memory system design, covering CLAUDE.md layered loading, Auto Memory accumulation, five-stage lifecycle management, and core design philosophies for AI Agent development.
Read more →
·3 min
A 4-Week Roadmap to Getting Started with AI Agent Development from Scratch
A complete 4-week learning roadmap for AI Agent development from scratch, covering core theory, ReAct paradigm, multi-agent collaboration, Prompt optimization, and hands-on projects.
Read more →
·5 min
Harness: The Operating System That Takes LLM Agents from Demo to Production
Deep dive into Harness technology: how context engineering, memory management, and multi-agent architecture transform LLM agents from stochastic demos into stable production systems.
Read more →
·3 min
Gemini Outputs a Stranger's Name: The Privacy Risks Behind AI Memory Features
Google Gemini suddenly output a user's mother's name in conversation, sparking AI privacy debate. We analyze causes from hallucination, memory features, and data crosstalk perspectives.
Read more →