BestHub
Sign in
Tagged articles

AI Agent Memory

9 articles · Page 1 of 1
DataFunTalk
DataFunTalk
Oct 25, 2026 · Artificial Intelligence

EvoMemBench: Why AI Agent Memory Must Evolve, Not Just Remember

The article introduces EvoMemBench, a benchmark evaluating AI agent memory across four dimensions — task-internal knowledge, task-internal execution, cross-task knowledge, and cross-task execution — revealing five key findings: memory isn't always better than raw context, helps more on hard tasks, is critical for long-horizon execution, retrieval does not equal revision, and no single memory type fits all tasks. It concludes with five engineering principles for building effective memory systems.

AI Agent MemoryAgent EvaluationContinuous Learning
0 likes · 20 min read
EvoMemBench: Why AI Agent Memory Must Evolve, Not Just Remember
IT Architects Alliance
IT Architects Alliance
Oct 14, 2026 · Artificial Intelligence

Why Claude Code Still Runs npm After You Switched to pnpm: The Memory Invalidation Problem

This article analyzes why AI coding agents like Claude Code persistently execute outdated build commands despite updated rules, tracing how manual rules and automatic memory enter context, and proposes a governance framework with invalidation conditions, execution guards, and cross-session regression tests to keep memory aligned with current code.

AI Agent MemoryClaude CodePreToolUse
0 likes · 15 min read
Why Claude Code Still Runs npm After You Switched to pnpm: The Memory Invalidation Problem
Machine Heart
Machine Heart
Sep 30, 2026 · Artificial Intelligence

HaluMem: Evaluating Hallucinations in AI Agent Memory Systems

HaluMem introduces an operation-level benchmark for AI agent memory systems, evaluating extraction, update, and QA stages to uncover hallucinations; experiments on six systems show high recall often accompanies false memories, while low update hallucination rates mask massive omissions, and upstream memory errors propagate to final answers.

AI Agent MemoryEMNLP 2026HaluMem
0 likes · 15 min read
HaluMem: Evaluating Hallucinations in AI Agent Memory Systems
AI Step-by-Step
AI Step-by-Step
Sep 20, 2026 · Artificial Intelligence

TencentDB Agent Memory: Hierarchical AI Agent Memory Cuts Tokens 61%

Tencent Cloud's open-source TencentDB Agent Memory introduces a hierarchical L0–L3 memory system with symbolic short-term offloading to Mermaid canvases, achieving 61% token reduction on WideSearch and 33% on SWE-bench while preserving full drill-down traceability via node_id links, and integrates with Pi agents through a zero-code proxy.

AI Agent MemoryMermaidOpen Source
0 likes · 12 min read
TencentDB Agent Memory: Hierarchical AI Agent Memory Cuts Tokens 61%
Architecture Digest
Architecture Digest
Sep 7, 2026 · Artificial Intelligence

OpenViking: Open-Source Context Database for AI Agents with 32k GitHub Stars

OpenViking, an open-source context database from Volcano Engine with 32k GitHub stars, solves AI agent memory overflow by storing long-term memory, project resources, and skills in a virtual file system with three-layer summaries, traceable retrieval, and automatic memory consolidation, integrating with major coding agents like Codex and Cursor.

AI Agent MemoryAgent IntegrationContext Database
0 likes · 11 min read
OpenViking: Open-Source Context Database for AI Agents with 32k GitHub Stars
JD Cloud Developers
JD Cloud Developers
Sep 1, 2026 · Artificial Intelligence

Claude Code vs Codex: Deep Architectural Comparison of AI Agent Memory Systems

This article provides an architecture-level comparison of Claude Code's four-layer automated memory system (CLAUDE.md, Auto Memory, Session Memory, AutoDream) versus Codex's two-layer manual declarative system (AGENTS.md + Session Context), analyzing persistence strategies, cross-session transfer, context compression, MCP support, and design philosophy trade-offs between automation and controllability.

AGENTS.mdAI Agent MemoryAutoDream
0 likes · 52 min read
Claude Code vs Codex: Deep Architectural Comparison of AI Agent Memory Systems
Code Ape Tech Column
Code Ape Tech Column
Aug 28, 2026 · Databases

Redis Transforms into AI Data Infrastructure: Vector Search, Vector Sets, Semantic Cache & Agent Memory

This article details Redis's evolution into a comprehensive AI data infrastructure, covering its four core capabilities—vector search with hybrid queries, native Vector Sets data type, LangCache semantic caching for 70% LLM cost reduction, and Redis Iris context engine for AI agent memory—with technical implementations, performance benchmarks, and use-case recommendations.

AI Agent MemoryHNSWJava
0 likes · 16 min read
Redis Transforms into AI Data Infrastructure: Vector Search, Vector Sets, Semantic Cache & Agent Memory