OpenAI Agents SDK

Search everything

Mentions · 7d0
Mentions · 30d1
All mentions3
First seenSep 17, 2026
Last mentioned19d ago

Timeline

3 articles · newest first

Larger gpt-oss agents gain no MCP fault tolerance, study finds

MCP-Injector, calibrated on 57,240 threads from 1,774 repositories, cut task scores 60 percent, from 8.08 to 3.23.

arXiv cs.AI / cs.LG / cs.CLOct 23, 12:35 UTC · 19d agoAI research4 · 4 reads

Arcjet brings security controls and audit trails to AI agents

Arcjet launched agent runtime security, giving engineering and security teams observability, policy enforcement, and audit trails for AI agents in production.

Help Net SecuritySep 18, 08:55 UTC · Sep 18, 2026AI safety & security1 · 1 read

Loopjacking: Hijacking Human-in-the-Loop Approval

Loopjacking lets agent approvals authorize a different operation than the human reviewed.

arXiv cs.CRSep 17, 20:58 UTC · Sep 17, 2026AI safety & security2 · 1 read

Appears with

OpenAIvendor · 3
LangChainproduct · 2
Agno AgentOSproduct · 1
Claude Agents SDKproduct · 1
LangChainvendor · 1
Arcjetorganization · 1
Anthropicvendor · 1
LangGraph Agent Serverproduct · 1
Open Policy Agentproduct · 1
OpenTelemetryproduct · 1
gpt-oss 20Bai model · 1
Agnovendor · 1
MCP-Injectorproduct · 1
gpt-oss 120Bai model · 1
OpenClawproduct · 1
Microsoftvendor · 1

Entities are extracted by the model from each article. First seen Sep 17, 2026, last mentioned 19d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.