LangChain introduces managed connections for agent credentials
Managed Deep Agents v0.7 supports per-caller OAuth identity and secure credential storage in LangSmith without code changes.
See the latest news and media coverage for LangChain. We track all announcements, press releases, and industry mentions in real time, all in one place.
Platform for building, testing, deploying, and observing AI agents
langchain.comLast updated
In short: LangChain launched Managed Deep Agents in public beta, expanded LangSmith to AWS, and achieved ISO 27001 security certification.
Managed Deep Agents v0.7 supports per-caller OAuth identity and secure credential storage in LangSmith without code changes.
The platform integrates with Slack and Linear, supports self-hosted deployments, and introduces reduced analysis mode to control costs while automating root cause diagnosis and fix proposals.
This middleware enables secure, budget-controlled agentic commerce via x402 micropayments and integrates with LangSmith for auditing and evaluation.
Enterprises can run a managed LangSmith deployment in their own AWS account and VPC, keeping sensitive data within their boundary across 15 regions. LangChain operates the infrastructure.
NVIDIA and LangChain launched the NemoClaw for LangChain Deep Agents blueprint, pairing the open-weight Nemotron 3 Ultra model with a tuned harness that scored 0.86...
Attackers are actively exploiting path traversal and SQL injection in Langflow, LangGraph, and LangChain — below where your security tools look.
Three patched LangGraph flaws could let attackers chain SQL injection and unsafe deserialization for RCE in self-hosted deployments.
AI agent safety benchmark BeSafe-Bench tested 13 production-grade agents and found none could complete 40% of tasks while respecting all safety constraints. With EU AI...
Track LangChain and your other target companies to get real-time alerts and weekly summaries delivered straight to your inbox.
Browse news for competitors to LangChain and other trending companies.