DeepAgents

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

Visit DeepAgents

Key features

• LangChain agent ecosystem integration — Built directly on LangChain primitives, allowing custom agent graphs, tools, and harness extensions. - Terminal-based execution runtime — Executes code navigation, shell actions, and file modifications directly from developer environments. - LangSmith tracing and evaluation — Native hooks for monitoring agent execution traces, token consumption, and sandbox benchmarks. - Managed agent support (mda) — Transitioned tooling to the managed-deepagents CLI interface for executing coding agent workloads. - Evaluation harnesses — Dedicated libs/evals and automated test suites for benchmarking coding agent reliability across repositories. - Multi-model compatibility — Supports standard LLM providers configured through standard LangChain chat model interfaces.

Use cases

Use Case: Automated Repository Refactoring A developer configures DeepAgents to perform sweeping code updates across a Python repository, such as bumping minimum package dependencies and resolving downstream deprecation warnings across sub-libraries.

Use Case: Agentic Code Evaluation and Benchmarking An AI engineering team uses the libs/evals and runner infrastructure within DeepAgents to benchmark agent performance on realistic multi-file coding and debugging tasks.

Use Case: Non-Interactive Scripted Execution CI/CD pipelines leverage DeepAgents' non-interactive execution runners to validate pull requests, run linting adjustments, and produce automated remediation patches.

Who it is for

DeepAgents is targeted at Python developers, AI engineers, and teams already building within the LangChain and LangSmith ecosystems who need an extensible, code-focused agent harness. It is less suited for developers seeking an out-of-the-box, single-binary GUI/IDE assistant with zero configuration requirements.

Install guide

Installation Install the package via pip (or uv / poetry). Note that recent repository releases utilize the managed-deepagents (mda) package in place of legacy deepagents-cli: bash pip install managed-deepagents Alternatively, install directly from the source repository: bash git clone https://github.com/langchain-ai/deepagents.git cd deepagents pip install -e .

First Run Configure your environment with your preferred model provider API keys and optional LangSmith telemetry: bash export OPENAI_API_KEY="your-openai-key" export ANTHROPIC_API_KEY="your-anthropic-key" # Optional LangSmith tracing export LANGCHAIN_TRACING_V2="true" export LANGCHAIN_API_KEY="your-langsmith-key"

Example Session Run the CLI client within your target project directory to inspect and execute tasks: bash mda run "Audit libs/ for deprecated import warnings and generate a summary report"

Part of CLI Coding Agents

Categories: AI Coding Agents, Chatbot Development, Developer Tools

Related CLI agents

• Agentlas-OS — Agentlas-OS is an open-source agent runtime fabric and orchestrator developed by Agentlas AI. It is designed to standardize, coordinate, and…
• SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
• Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…
• Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
• Stratless — Stratless is an open-source agent harness and execution orchestrator developed by the Stratless AI team. It provides a modular infrastructure…
• Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…