DeepAgents is an open-source agentic coding framework and CLI tooling suite maintained by LangChain (langchain-ai). Designed to bring autonomous agent execution to local development workflows, it bridges LangChain's agent orchestration infrastructure with coding-specific harness environments. In daily use, DeepAgents executes commands, inspects project trees, edits code, and automates multi-step development tasks from the terminal. The framework leverages the broader LangChain ecosystem for model routing, allowing developers to configure standard commercial LLM backends (such as OpenAI and Anthropic) as well as self-hosted models via standard API endpoints and environment configurations. What distinguishes DeepAgents from standalone CLI coding assistants is its deep integration into LangChain's agent architecture and evaluation tooling (including LangSmith tracing and sandbox environments). Development in the repository centers on modular libraries such as core execution runtimes (`libs/code`), evaluation harnesses (`libs/evals`), and managed orchestration clients (`managed-deepagents` / `mda`), replacing earlier iterations of `deepagents-cli`. DeepAgents is distributed as open-source software under standard permissive licensing on GitHub and packaged for Python via PyPI.
Tags: agent harness, ai agent, cli, developer tools, Generative AI, OpenSource