# langchain-ai/deepagents

The batteries-included agent harness.

Repository: https://github.com/langchain-ai/deepagents
Canonical: https://ross.abutalabs.com/products/deepagents
Homepage: https://docs.langchain.com/deepagents
Language: Python
License: MIT
License Family: permissive
Topics: deepagents, langchain, langgraph, ai, python, typescript
Last push: 2026-08-27T00:31:40+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 28
- inputs: {"age_days": 402, "days_push": 7, "days_rel": 7, "gap_med": 0, "n_releases_24m": 246}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 28559, forks 4000 (observed 2026-08-28T04:11:48.377610+00:00)

## What it is
Deep Agents is an open-source, batteries-included agent harness from LangChain built on LangGraph, providing an opinionated agent with filesystem tools, sub-agent delegation, context management, persistent memory, and human-in-the-loop approval out of the box. It is model-agnostic (works with any tool-calling LLM), available in Python and TypeScript, and every component can be extended, overridden, or replaced.

## Use cases
- build an AI agent that can plan and execute multi-step tasks
- delegate subtasks to subagents with isolated context windows
- give an LLM agent file read/write/search and shell access
- build a research agent that writes reports
- add human approval before an agent runs tools
- run a coding agent in the terminal powered by any LLM
- persist agent memory across sessions
- connect an agent to MCP servers and custom tools

## When to choose
- you want a production-ready agent with sensible defaults for long-horizon, multi-step work
- you need subagents, filesystem tools, context summarization, and memory without building them yourself
- you want model-agnostic agents that work with OpenAI, Anthropic, Google, or local models
- you're already in the LangChain/LangGraph ecosystem and want tracing and deployment via LangSmith

## When to avoid
- you need a minimal, unopinionated agent loop and prefer to assemble everything yourself
- your LLM does not support tool calling
- you want a fully managed no-code agent builder rather than a code framework
- you need a framework outside the LangChain ecosystem with no LangGraph dependency

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, mcp, file-system, chatbot
- domain: large-language-models, developer-tools
- platform: python, cross-platform, cli
- tags: agent-harness, subagents, context-management, langgraph, human-in-the-loop, long-horizon-tasks, skills, model-agnostic, ai-agents, automation, nodejs

## Member repositories
- langchain-ai/deepagents (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:48.377610+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:54:21.696312+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/deepagents (fetched 2026-08-28T04:11:48.377610+00:00, sha aa6b8027fa03)
  - homepage: https://docs.langchain.com/deepagents (fetched 2026-08-29T07:50:52.263953+00:00, sha a6d02b8234ce)
  - site_page: https://docs.langchain.com/use-these-docs (fetched 2026-08-29T07:50:52.344594+00:00, sha 5ab7220bb555)
  - site_page: https://docs.langchain.com/oss/python/deepagents/quickstart (fetched 2026-08-29T07:50:52.297696+00:00, sha c2dcf9bbe1c5)
  - site_page: https://docs.langchain.com/oss/python/releases/changelog (fetched 2026-08-29T07:50:52.320229+00:00, sha 048dded673bc)
  - site_page: https://docs.langchain.com/langsmith/observability-quickstart (fetched 2026-08-29T07:50:52.339963+00:00, sha e2173e54f36b)
  - site_page: https://docs.langchain.com/oss/python/integrations/middleware (fetched 2026-08-29T07:50:52.342366+00:00, sha 7801c289afbb)
  - site_page: https://docs.langchain.com/ (fetched 2026-08-29T07:50:52.268115+00:00, sha e6cbe67a291c)
  - site_page: https://docs.langchain.com/oss/python/integrations/providers/overview (fetched 2026-08-29T07:50:52.270714+00:00, sha 8260e6c475ce)
  - registry_pypi: https://pypi.org/pypi/deepagents/json (fetched 2026-08-29T07:50:52.355036+00:00, sha f66c258c31e8)
- Data as of 2026-08-30T08:39:29.467469+00:00.