Langchain is a publication focusing on programming languages, language design, and compiler development. Readers can explore articles covering topics such as language features, syntax design, and compiler optimization techniques. Additionally, they can learn about programming language theory, language implementation challenges, and practical applications of language design principles.

LangChain

Traditional LLM agents that simply call tools in a loop are limited in handling complex, long-term tasks. Deep agents overcome these limitations through four key components: detailed system prompts with examples, planning tools (like todo lists), sub-agents for task decomposition, and file systems for context management. Applications like Claude Code, Deep Research, and Manus demonstrate this architecture's effectiveness. The author introduces an open-source 'deepagents' package that implements these patterns, making it easier to build specialized deep agents for specific domains.

Deep Agents

<p>Curious why he thinks Claude Code’s todolist is no-op.</p>
<p>That’s certainly true for the sequential thinking MCP, but Claude Code’s todo list tool, does actually store a todo list, with priorities and completion status into json files.</p>
