Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The release introduces a user-owned, local-first memory layer that persists AI agent context across sessions and tools, directly addressing the session-reset limitation that causes repeated re-explanation of architectural decisions in tools like Claude Code and Cursor.
NRT-Bench reveals that frontier LLM agents are vulnerable to adaptive multi-turn attacks even in safety-critical supervisory roles, and that model-specific, nearly non-overlapping failure modes mean aggregate robustness metrics can mask significant individual weaknesses.
Ego lite removes the last-mile browser bottleneck for coding agents by letting them operate inside authenticated, real-world browser sessions rather than blank headless profiles where login flows and two-factor authentication break automation.
The structured shared history design directly resolves the tradeoff between inter-module context blindness and context rot, recovering cache prefix consistency while keeping per-module token consumption bounded in enterprise agentic systems.
The post identifies a gap in standard AI cost tooling: provider dashboards report spending after calls execute, but agents can accumulate runaway costs across many steps before any dashboard alert fires, making a pre-call interception layer the only point where spending can actually be stopped.
The addition of GitHub and Slack triggers alongside computer use support expands Cursor Automations beyond its previous trigger set, enabling agents to respond to a broader range of external events.
The paper provides a measurable, formal account of how evaluation bias spreads in multi-agent LLM pipelines and identifies a concrete structural intervention — expanding evaluator committee size — that reduces that spread by 72.4%.
EMA replaces thousands of manual, per-user OAuth consent flows with centralized IdP-governed authorization, closing the audit, offboarding, and compliance gaps that standard MCP auth leaves open at enterprise scale.
Cursor's mobile app and cloud-agent migration capability let agents continue running after a developer closes their laptop, decoupling coding work from the local machine.
Iris replaces screenshot-based or assumption-based verification with runtime evidence from a live app, giving coding agents a concrete, structured verdict on whether their changes actually worked.