How Deep Agents Run Untrusted Code Without a Sandbox
Deep Agents introduces dynamic subagents that use WebAssembly (WASM) and QuickJS to execute untrusted code securely, ensuring isolation and preventing compromise of the host environment. The system enforces capability isolation, limiting agents to predefined actions and data access, while a harness manages execution and execution limits. Durable pauses allow agents to wait for human input without rebuilding the program, maintaining execution integrity. Two public, experimental packages—quickjs-rs and langchain-quickjs—enable secure execution of untrusted code, integrating with production systems.
More from Langchain
Why managed agents are the next big thing in agent building
Managed Deep Agents gives developers a managed way to build, run, and deploy Deep Agents with built-in runtime, streaming, sandboxes, evals, memory, and auth.
langchain.com··Mads Kristian Nylund·AI InfrastructureAI-agents
LangSmith BYOC on AWS is generally available
LangSmith Bring Your Own Cloud is now generally available on AWS, giving Enterprise teams managed observability, evaluation, and deployment inside their own VPC.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI Platforms
What is an AI agent?
Learn what AI agents are, how they work in an LLM loop, and where workflows fit so you can build reliable, production-ready autonomous systems.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI-agents