OSSverl-agent GiGPO: Per-Step Credit Assignment for Agent RLGitHub·high signal12%+ ALFWorld improvement. Train 7B on 2 H100s. Accepted NeurIPS 2025.SourceSource pageGitHub↳ Follow the threadPolicy dependency / Stack layerCynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write PermissionsIT Security NewsStack layer / Threat pattern'Ghost Commit' Disclosure: PNG-Hidden Prompt Injection Makes Cursor and Anti-Gravity Exfiltrate .env Secretsawesome-ai-agent-attacks timelineThreat pattern / Update threadMicrosoft Agent Framework python-1.11.0 adds Progressive MCP Disclosure and GA Skills APIGitHub (Microsoft Agent Framework)Stack layer / Update threadclaude-video Turns 'Watch This Video' Into a Portable Agent Skill — 8K Stars in WeeksGitHubStack layer / Update threadShow HN: Jacquard — A Programming Language for AI-Written, Human-Reviewed CodeGitHub / Hacker NewsPolicy dependency / Stack layerCodenotary ships AgentMon 3 for agent runtime policy and compliance loggingAI Agent StoreStack layerAgno Pitches Sub-Microsecond Agent Instantiation as the Speed Play in FrameworksGitHubStack layerAnythingLLM Repositions Around 'Own Your Intelligence' With a Local-First Agent StackGitHub