ToolsPageIndex Vectorless RAG 98.7 Percent AccuracyGitHub·high signalHierarchical tree indexing + LLM reasoning instead of embeddings. 98.7% accuracy on FinanceBench. Paradigm challenge to vector RAG.SourceSource pageGitHub↳ Follow the threadStack layerShow HN: Clawk Gives Coding Agents a Disposable Linux VM Instead of Your LaptopGitHub / Hacker NewsPolicy dependency / Stack layerCynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write PermissionsIT Security NewsSame source domain / Semantic neighborTencent Ships Fully-Local 4-Tier Agent Memory With Hard Benchmarks — No External APIGitHubStack layer / Threat pattern'Ghost Commit' Disclosure: PNG-Hidden Prompt Injection Makes Cursor and Anti-Gravity Exfiltrate .env Secretsawesome-ai-agent-attacks timelineStack layer / Update threadShow HN: Jacquard — A Programming Language for AI-Written, Human-Reviewed CodeGitHub / Hacker NewsStack layer / Update threadclaude-video Turns 'Watch This Video' Into a Portable Agent Skill — 8K Stars in WeeksGitHubThreat pattern / Update threadMicrosoft Agent Framework python-1.11.0 adds Progressive MCP Disclosure and GA Skills APIGitHub (Microsoft Agent Framework)Policy dependency / Threat patternTool-Grounded LLM Agent 'TerraRepair' Lifts Terraform Security Fix Rates From 26.6% to 78.4%arXiv