> ## Documentation Index > Fetch the complete documentation index at: https://docs.langchain.com/llms.txt > Use this file to discover all available pages before exploring further. # Build > Build agents with LangChain, LangGraph, and Deep Agents using Python.

Build

The LangChain open source stack provides the building blocks you need to design, test, and ship agents.

Choose your starting point

Deep Agents, LangChain, and LangGraph share the same stack, so choose based on how much control you need: Build agents for complex, long-running tasks. A complete agent harness with planning, subagents, a virtual filesystem, and long-term memory built in. The fastest way to start. A minimal, configurable agent framework. Compose exactly what you need from models, tools, prompts, and middleware. Low-level orchestration for stateful, long-running agents: durable execution, streaming, memory, and human-in-the-loop.

Use a ready-made agent

Open source terminal coding agent (`dcode`) built on the Deep Agents SDK. Switch models mid-session, customize skills and memory, and approve shell execution from the CLI.

Explore

Connect to model providers, vector stores, retrievers, and other components. Follow tutorials and conceptual guides for common agent patterns and use cases. API references, error codes, release notes, and migration guides. Contribute documentation, code, and integrations to the LangChain ecosystem.
***
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers. [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/build-overview.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).