Agent-Lab is a robust toolkit engineered for the development and thorough testing of Large Language Model (LLM) agents. It offers key features designed to streamline the process, including a REST API for managing interactions, relational persistence with PostgreSQL for data storage, and secure secrets management using Vault. In addition, Agent-Lab emphasizes observability through OpenTelemetry for detailed insights and leverages PgVector for effective vector storage and search, ultimately providing a comprehensive platform for building and evaluating LLM-powered agents.
- Support researchers and developers with a comprehensive toolkit for developing, testing, and experimenting with LLM agents, including example implementations.
- Provide an MCP server interface for agent discovery, dialog history, and agent-to-agent communication.
- Offer integration testing support to ensure quality assurance.
- Deliver observability for responsible AI explainability and agent evaluation.
- Leverage a cloud-native architecture for seamless deployment and scalability.
- REST API: Manage integrations with AI suppliers, LLMs settings, agents, and conversation histories with our REST API.
- MCP Server: Utilize the Model Control Protocol (MCP) server for agent discovery, dialog history, and agent-to-agent communication.
- Observability: Obtain detailed insights through logs, metrics, and traces powered by OpenTelemetry.
- Includes reference implementations for Grafana and OpenSearch Dashboards.
- Cloud-Native: Optimized for cloud environments with Docker, Kubernetes, and Helm charts for streamlined deployment.
- Relational Persistence: Store data reliably using PostgreSQL to support the entity domain model for prompts, agent-specific settings, conversations, and more.
- Secrets Management: Securely store and retrieve secrets with Vault.
- Vector Storage and Search: Efficiently manage vector data using PgVector for similarity search and retrieval.
- Agent Memory: Using PostgreSQL checkpointer to store and retrieve agent memory, enabling agents to maintain context across interactions.
- Integration Testing: Ensure reliability and correctness with a comprehensive integration test suite.
Agent-Lab features a MCP Server that allows agent discovery (get_agent_list tool), dialog history (get_message_list tool) and agent-to-agent communication (post_message tool).
The following example shows MCP Server discovering and obtaining dialog history of a supervised coder agent instance:
Please refer to MCP guide for more details.
Note: Claude Desktop is used only for demonstration purposes. This project is not affiliated with Anthropic AI.
Agent-Lab is designed for ease of setup and use, whether you're a developer building LLM agents or a researcher experimenting with agentic workflows.
Documentation in this repository is divided into two main sections:
- Developer's Guide: Tailored for developers who want to customize Agent-Lab or build agentic workflows. It includes setup instructions and development practices. Please refer to our developer's guide.
- Researcher's Guide: Provides detailed instructions for researchers on setting up and using Agent-Lab, including how to run the MCP server, manage agents, conduct experiments, tune prompts, and prototype new agents. Please refer to our researcher's guide.
Please consult these guides for detailed instructions on getting started with Agent-Lab.
Community support is greatly appreciated. If you encounter any issues or have suggestions for enhancements, please report them by creating an issue on our GitHub Issues page.
Refer to our developer's guide for instructions on how to contribute to the project.
This project is licensed under the MIT License. See the LICENSE file for details.