deepagents
Gives you a ready-made agent for long, multi-step coding work that can delegate subtasks to sub-agents, manage its own context, keep memory across sessions, and ask you to approve tool calls before they run.
2 skills31k
@langchain-ai- 32,492Stars earned
- 2Plugins
- 24Skills
- 2MCP servers
Plugins
2@langchain-aiAuto-invoked
langchain-skills
Agent skills for building agents with LangChain, LangGraph, and Deep Agents. Covers Deep Agents setup, memory and filesystem backends, subagents, task planning, and human-in-the-loop approval.
22 skills1.3k
@langchain-aiSkills
24configuration-hardenin…
Review Talon tool placement and defensive prompts when requested or when adding or changing tools or subagents; apply confirmed…
@langchain-aiAuto-invoked
deep-agents-core
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format,…
@langchain-aiAuto-invoked
deep-agents-memory
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral),…
@langchain-aiAuto-invoked
deep-agents-orchestrat…
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for…
@langchain-aiAuto-invoked
deepagents-python-quic…
Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of…
@langchain-aiAuto-invoked
deepagents-typescript-…
Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead…
@langchain-aiAuto-invoked
ecosystem-primer
INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any…
@langchain-aiAuto-invoked
eval-engineering
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and…
@langchain-aiAuto-invoked
langchain-dependencies
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for…
@langchain-aiAuto-invoked
langchain-fundamentals
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
@langchain-aiAuto-invoked
langchain-middleware
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers…
@langchain-aiAuto-invoked
langchain-python-quick…
Scaffold a minimal local LangChain agent in Python by following the official quickstart. Use when the user wants to quickly build…
@langchain-aiMCP servers
2docs-langchain
MCPLooks up guidance in the documentation of an open-source framework for building LLM-powered applications and agents.
@langchain-aireference-langchain
MCPLooks up reference documentation and usage examples for building applications with the LangChain framework.
@langchain-aiIs this you? Claim your profilePut a plugin at the top of Plugins, from $9