Deep Agents Core
This is a comprehensive wrapper around LangChain that adds production-ready middleware for complex AI workflows. Instead of building task planning, file management, and delegation logic yourself, you get TodoListMiddleware for breaking down work, filesystem tools with pluggable backends, and SubAgent spawning out of the box. The skill system uses progressive disclosure, loading SKILL.md files only when relevant rather than cramming everything into context upfront. Use this when you need persistent memory across sessions, human approval workflows, or agents that can delegate specialized work to subagents. It's opinionated but handles the plumbing so you focus on configuration rather than middleware implementation.
- skills.sh installs
- 16.7K
- GitHub stars
- 1.3K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add langchain-ai/langchain-skills --skill deep-agents-core --agent claude-codeInstalls into .claude/skills of the current project.
Files
- Task Planning: TodoListMiddleware for breaking down complex tasks
- Context Management: Filesystem tools with pluggable backends
- Task Delegation: SubAgent middleware for spawning specialized agents
- Long-term Memory: Persistent storage across threads via Store
- Human-in-the-loop: Approval workflows for sensitive operations
- Skills: On-demand loading of specialized capabilities
The agent harness provides these capabilities automatically - you configure, not implement.
| Use Deep Agents When | Use LangChain's create_agent When |
|---|---|
| Multi-step tasks requiring planning | Simple, single-purpose tasks |
| Large context requiring file management | Context fits in a single prompt |
| Need for specialized subagents | Single agent is sufficient |
| Persistent memory across sessions | Ephemeral, single-session work |
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/langchain-ai/langchain-skills
- Categories
- Code Review & Quality, AI & Agent Building
More from langchain-ai/langchain-skills
All 15- Managed Deep Agents10K
- Langgraph Cli9.7K
- Swarm9.5K
- Ecosystem Primer8.8K
- Framework Selection7.7K
- Deep Agents Memory19.8K
- Langgraph Fundamentals18.9K
- Langgraph Persistence18.8K
- Langchain Rag18.4K
- Langchain Fundamentals18.2K
- Langgraph Human In The Loop18K
- Langchain Middleware17K
- Deep Agents Orchestration16.8K
- Langchain Dependencies16.8K
Recommended
More Code Review & Quality
nature-revieweryuan1z0825/nature-skillsSimulate Nature-style or general pre-submission peer review from the referee perspective, not an author rebuttal. Use for reviewer reports, mock peer review, ma14.8Kskills.sh installs
ultracitehaydenbleasel/ultraciteUltracite is a zero-config linting and formatting preset for JavaScript/TypeScript projects. Use when: (1) Setting up or initializing Ultracite in a project (ul13.2Kskills.sh installs
mobile-app-ui-designceorkm/mobile-app-ui-designDesign high-quality mobile app UI/UX screens, flows, and components. Use this skill whenever the user asks to design a mobile app screen, create app mockups, bu12.7Kskills.sh installs
create-implementation-plangithub/awesome-copilotCreate a new implementation plan file for new features, refactoring existing code or upgrading packages, design, architecture or infrastructure.12.6Kskills.sh installs
security-best-practicesopenai/skillsPerform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best pr12.2Kskills.sh installs
academic-paperimbad0202/academic-research-skills12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebut11.4Kskills.sh installs