LangChain
Coverage of LangChain in the Nexus archive.
- LangGraph Flaw Chain Exposes Self-Hosted AI Agents to Remote Code Execution
Cybersecurity researchers disclosed three patched security flaws in LangGraph, an open-source framework by LangChain for building AI agents, including a critical vulnerability chain that could lead to remote code execution.
- Interesting shift happening quietly
Agent Cards offers a solution for companies to manage AI agent spending via dedicated corporate cards funded by USDT. It enforces spending rules server-side, logs transactions in real-time, and integrates with frameworks like LangChain, OpenAI, and Claude. Setup is quick, and the system eliminates shared cards, manual approvals, and financial surprises.
- Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis
Agent-cache is a multi-tier caching solution for AI agents using Valkey or Redis, supporting LLM responses, tool results, and session state. It integrates with LangChain, LangGraph, and Vercel AI SDK, and includes monitoring via OpenTelemetry and Prometheus. Version 0.2.0 was recently released with cluster mode support.