---
slug: "deep-agents"
name: "Deep Agents"
effect: "Gives you a ready-made agent harness with planning, files, subagents and context management"
category: "agent-framework"
tier: "standard"
url: "https://docs.langchain.com/oss/python/deepagents/overview"
github: "langchain-ai/deepagents"
pricing: "open-source"
license: "MIT"
tags: ["python", "agent-harness", "subagents", "langgraph", "langchain", "mcp"]
platforms: []
install_kind: "pip"
date_added: "2026-10-15"
rank: null
rising_score: 55
stars: 30277
star_velocity: 68.2
velocity_basis: "since creation"
created_at: "2025-07-27T23:07:53Z"
pushed_at: "2026-10-15T04:36:48Z"
signals_status: "ok"
signals_fetched_at: "2026-10-15T05:02:35.392Z"
page: "https://agenttooldrop.com/tools/deep-agents"
---

# Deep Agents

Gives you a ready-made agent harness with planning, files, subagents and context management

Category: Agent frameworks. Tier: standard (a well-known tool, listed for reference, not ranked). Pricing: Open source. License: MIT.

## Why you would want it

Deep Agents is LangChain's opinionated agent harness on top of LangGraph, with subagents that get isolated context windows, a filesystem over local, sandboxed or remote backends, shell access, summarization of long threads and human approval of tool calls. It works with any model that supports tool calling, including local models through Ollama, vLLM or llama.cpp, and accepts your own tools or MCP servers. A JS/TS version lives in a separate repo, deepagentsjs.

## Best for

- Long-horizon, multi-step agents
- Teams already on LangChain or LangGraph
- Agents that need subagents and file access

## Use it when

You want planning, subagents, files and context management working on day one, and still want to override any piece.

## Skip it if

You need a custom control flow; LangGraph underneath gives you that directly. Its security model trusts the LLM, so you must enforce limits at the tool or sandbox level.

## Install

Install with uv:

```sh
uv add deepagents
```

Source: https://github.com/langchain-ai/deepagents#readme

## Live signals

Fetched 2026-10-15T05:02:35.392Z (status: ok).

- Repository: langchain-ai/deepagents
- Repository created: 2025-07-27
- Stars: 30,277 (GitHub's count; it cannot be authenticated)
- Stars per day, since repo creation: 68.2 (an average over the repo's life, not a growth rate)
- Forks: 4,253
- Open issues and PRs: 192
- License (GitHub): MIT
- Last push: 2026-10-15
- Latest release: deepagents==0.7.25 (2026-10-14)

## Links

- Website: https://docs.langchain.com/oss/python/deepagents/overview
- GitHub: https://github.com/langchain-ai/deepagents
- Install instructions verified at: https://github.com/langchain-ai/deepagents#readme
- Source for this entry: https://github.com/langchain-ai/deepagents#readme
- AgentToolDrop page: https://agenttooldrop.com/tools/deep-agents
- Full catalog (JSON): https://agenttooldrop.com/tools.json