langgraph and qd-langchain-agents

LangGraph provides the foundational graph-based agent orchestration framework, while QD-LangChain Agents is a research tool that uses evolutionary algorithms to optimize agent architectures built within that framework—making them complements where one enhances the other.

langgraph
86
Verified
qd-langchain-agents
38
Emerging
Maintenance 22/25
Adoption 15/25
Maturity 25/25
Community 24/25
Maintenance 2/25
Adoption 6/25
Maturity 15/25
Community 15/25
Stars: 26,286
Forks: 4,544
Downloads:
Commits (30d): 130
Language: Python
License: MIT
Stars: 17
Forks: 5
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: MIT
No risk flags
Stale 6m No Package No Dependents

About langgraph

langchain-ai/langgraph

Build resilient language agents as graphs.

This tool helps developers create sophisticated, long-running AI assistants that can remember past interactions and handle complex, multi-step tasks. It takes raw code logic and structured data, producing robust AI agents capable of sustained operation and intelligent decision-making. Developers and AI engineers will use this to build advanced conversational agents, automated workflows, or intelligent systems.

AI Agent Development Conversational AI Automated Workflows Intelligent Systems Machine Learning Engineering

About qd-langchain-agents

FareedKhan-dev/qd-langchain-agents

Evolving LangChain agent architectures using the Quality-Diversity (QD) algorithm.

This project helps AI developers build more robust and versatile AI agents or RAG systems by automating the design process. It takes a conceptual design for an AI agent or RAG system and generates numerous diverse and high-performing architectural blueprints. AI developers can use this to overcome the limitations of manual design and find novel solutions.

AI-architecture-design RAG-system-optimization agent-development evolutionary-algorithms AI-system-design

Scores updated daily from GitHub, PyPI, and npm data. How scores work