langchain-ai/deepagentsjs

Health v2 · maintenance only

Adoption not part of the score

1507 stars · 262 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Deep Agents (deepagentsjs) is a TypeScript library from LangChain for building controllable LLM-powered agents on top of LangGraph. It provides a batteries-included agent harness with built-in file system tools for context management, subagent spawning, task planning, long-term memory, and human-in-the-loop approval.

Use cases

• build ai agents that plan and execute multi-step tasks
• spawn subagents with isolated context windows
• give agents file system read/write tools for context management
• build a research agent that writes reports
• add human approval checkpoints to agent workflows
• run background subagent tasks while user keeps chatting
• build agents with long-term memory and skills

When to choose

• you want a batteries-included agent harness instead of assembling LangGraph primitives yourself
• your agent needs subagent delegation, planning, and file-based context offloading
• you're already in the LangChain/LangGraph JavaScript ecosystem
• you need human-in-the-loop pauses at critical decision points

When to avoid

• you need a simple single-prompt LLM call with no tooling
• you're not using a model that supports tool calling
• you want a Python agent framework (use the Python deepagents package instead)
• you need fully managed agent hosting rather than a code library

Facets

library · maturity active

agent-framework llm-inference prompt-engineering rag artificial-intelligence large-language-models developer-tools cross-platform deep-agents subagents agent-harness file-system-tools context-management human-in-the-loop langgraph task-planning long-term-memory ai-agents nodejs typescript

Member repositories

For agents

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