Langroid
ActiveDescription
Langroid is a Python multi-agent programming framework that leverages an intuitive Agent-Task-Tool abstraction to help developers build LLM-powered multi-agent applications.
Key Features
- Multi-agent programming: intuitive Agent-Task-Tool abstraction inspired by the Actor Framework
- LLM-agnostic: works with practically any LLM, including local models via OpenAI-compatible APIs
- MCP tool adapter: convert MCP server tools into Langroid ToolMessage instances
- DocChatAgent: built-in RAG capabilities for document question answering
- Structured information extraction: multi-agent pipelines for extracting structured data from unstructured text
- Claude Code plugin: accelerate development with built-in patterns and best practices
Use Cases
💡 Building multi-agent collaborative systems for complex problem solving
💡 Creating RAG applications with document retrieval and question answering
💡 Extracting structured information from reports, invoices, or contracts
💡 Connecting LLM agents to external tools via MCP protocol integration
💡 Rapid prototyping of LLM applications with minimal framework overhead
Categories
Quick Start
Install via 'pip install langroid', import as 'import langroid as lr', set up an LLM config with lm.OpenAIGPTConfig, create a ChatAgent, wrap it in a Task, and call task.run(). See the Colab notebook or examples repo for multi-agent patterns.