Skip to main content

A LangChain-based crew management system

Project description

LangCrew

High-level multi-agent framework built on LangGraph - combines CrewAI's simplicity with enterprise-grade capabilities

LangCrew bridges the gap between LangGraph's flexibility and CrewAI's simplicity, offering pre-built agent orchestration, memory management, and production-ready features that eliminate the complexity of multi-agent development.

Quick Start

Install LangCrew:

pip install langcrew

Create your first multi-agent workflow:

import os
# Note: You'll need to install: pip install langchain-openai
from langchain_openai import ChatOpenAI
from langcrew import Agent, Task, Crew

# Create agents
researcher = Agent(
    role="Research Analyst",
    goal="Find and analyze information about any topic",
    backstory="You excel at finding key information and insights",
    llm=ChatOpenAI(model="gpt-4.1", api_key=os.getenv("OPENAI_API_KEY"))
)

writer = Agent(
    role="Content Writer", 
    goal="Create engaging content based on research",
    backstory="You're skilled at turning complex information into clear, compelling content",
    llm=ChatOpenAI(model="gpt-4.1", api_key=os.getenv("OPENAI_API_KEY"))
)

# Define tasks
research_task = Task(
    description="Research the latest trends in {topic}",
    agent=researcher,
    expected_output="A comprehensive analysis of current trends"
)

write_task = Task(
    description="Write a blog post about the research findings",
    agent=writer,
    expected_output="A well-structured blog post"
)

# Create and run crew
crew = Crew(
    agents=[researcher, writer],
    tasks=[research_task, write_task]
)

result = crew.kickoff(inputs={"topic": "AI agents"})
print(result)

That's it! Your agents will collaborate to research and write about any topic you choose.

Core Capabilities

Intelligent Orchestration - LangGraph-Powered Workflow Engine

State-driven agent coordination with optimized graph compilation, supporting sequential pipelines, conditional routing, and parallel execution patterns. Built-in context propagation ensures seamless information flow between agents.

Multi-Layer Memory Architecture - Persistent Knowledge Systems

Hierarchical memory with short-term, long-term, and entity storage. Native PostgreSQL/Redis backends with vector similarity search. Thread-based conversation continuity and cross-session knowledge retention.

Human-in-the-Loop Workflows - Enterprise HITL Integration

Configurable interruption points with approval mechanisms. Supports pre/post task interventions, critical decision checkpoints, and async human feedback loops. Full bilingual UI components for seamless interaction.

Real-time Event Streaming - Async Execution & Monitoring

Token-level streaming with granular event dispatch. Monitor agent thoughts, tool calls, and intermediate results in real-time. Supports WebSocket/SSE for live UI updates with v2 event protocol.

Flexible Task Execution - Advanced Orchestration Patterns

Dynamic task dependencies with context inheritance. Conditional execution based on outputs, retry mechanisms with exponential backoff, and parallel task processing with result aggregation.

Documentation

Core Concepts

  • Agents: Learn about intelligent agent creation and configuration
  • Tasks: Understand task definition and orchestration
  • Crews: Master multi-agent coordination and workflows

Related Projects

LangCrew builds on the shoulders of giants:

Contributing

You are welcome to open issues or submit PRs to improve this app, however, please note that we may not review all suggestions.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Next Steps

Learn More: Complete Documentation | Examples | API Reference

Ready-to-Use: Recruitment System | Marketing Strategy | Travel Planning

Get Help: GitHub Issues | Discussions

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langcrew-0.1.1.tar.gz (115.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

langcrew-0.1.1-py3-none-any.whl (136.7 kB view details)

Uploaded Python 3

File details

Details for the file langcrew-0.1.1.tar.gz.

File metadata

  • Download URL: langcrew-0.1.1.tar.gz
  • Upload date:
  • Size: 115.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.17

File hashes

Hashes for langcrew-0.1.1.tar.gz
Algorithm Hash digest
SHA256 73cd60a7c5ca267976d5efb21b9777767564258cbd4529200dbe2bcc0d64707e
MD5 d68026f3fae75d9d6519f9aef30c69d5
BLAKE2b-256 f9aa792d01fff6fb8d14c08eadb7e5e62f0de11a9262c2f6fba3a9c76abbcbf1

See more details on using hashes here.

File details

Details for the file langcrew-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: langcrew-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 136.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.17

File hashes

Hashes for langcrew-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a3c931253147841e465a80a98a07a633bb3d8d05b6e8fd524e45108e7e9b8ac4
MD5 e34dd1929d3a0383e1d3003ac6ab88c1
BLAKE2b-256 0327a374f97b60d819c5e65abeaae13fdec59f767300a36b56d35cf0db484e5f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page