DeepAgents

Health v2 · maintenance only

Adoption not part of the score

30425 stars · 4292 forks observed · 2026-10-20

What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-05, confidence 0.97

Deep Agents is a production‑ready, extensible agent harness for building LLM‑driven applications. It provides built‑in filesystem access, context management, sub‑agent delegation, skills, and long‑term memory.

Use cases

• build multi‑step AI assistants that need to read/write files and manage long context
• create research agents that can browse the web, summarize information, and store results
• develop autonomous agents that delegate tasks to specialized sub‑agents
• implement AI tools with human‑in‑the‑loop approval for critical actions
• add persistent memory to LLM agents across sessions

When to choose

• you need a batteries‑included framework that works out of the box with any LLM supporting tool calling
• your application requires file system interaction, long‑term memory, or sub‑agent orchestration
• you want deep integration with LangChain and LangGraph for tracing, persistence, and deployment
• you prefer an opinionated but fully extensible architecture without forking the core code

When to avoid

• you are looking for a lightweight, single‑function library without built‑in agent orchestration
• your project targets non‑Python environments exclusively
• you need fine‑grained control over every component and prefer building from scratch

Facets

library · maturity active

api-framework middleware state-management artificial-intelligence large-language-models chatbots python cross-platform deep-agents langchain langgraph tool-calling sub-agents filesystem persistent-memory human-in-the-loop retrieval-augmented-generation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="langchain-ai/deepagents")