Waldiez is an open-source suite designed to orchestrate AI agents for real-world, production environments, with a particular focus on applications in the physical world and edge deployment. The platform comprises two complementary tools: Wactorz, which provides runtime actor-model orchestration for autonomous agents, and Waldiez itself, a visual workflow builder for designing and executing multi-agent systems. Both components are aimed at engineers developing and deploying AI systems that require robust, scalable agent coordination.
Wactorz enables actor-model concurrency, where each agent operates in its own asynchronous loop with isolated mailboxes, ensuring no shared state or race conditions. Agents can be described in natural language and are spawned at runtime through LLM-based intent classification, supporting dynamic scaling without code changes or restarts. Communication between agents is managed via MQTT pub/sub, allowing for loose coupling and real-time telemetry, making the system suitable for edge and IoT scenarios. The platform includes built-in and customizable agents, such as MainActor, MonitorAgent, DynamicAgent, PlannerAgent, HomeAssistant agents, InstallerAgent, and CatalogAgent, with the ability to create and spawn user-defined agents. Additional features include a live dashboard for monitoring agent health, message flows, cost meters, and error alerts, as well as auto-persistence of agent state to ensure resilience against crashes and data loss. Deployment options include Docker, systemd, or a native Python runner, with remote node deployment supported via SSH.
The Waldiez visual workflow builder allows users to compose multi-agent flows using a drag-and-drop interface, connecting agents, tools, and data sources without manual orchestration code. Workflows can be exported to Python scripts or Jupyter notebooks with a single click, and the platform integrates with JupyterLab, VS Code, and Waldiez Studio. Real-time collaboration between agents is powered by the AG2 framework, and the Waldiez Hub provides a community layer for sharing, discovering, and forking multi-agent workflows, as well as building public portfolios. The system supports multi-LLM integration across major providers, and users can bring their own API keys and secrets.
0 license, with its components implemented in Python and Rust. It is particularly suited for engineers building AI-powered automation, event-driven pipelines, dynamic code execution, multi-step planning, health monitoring, and chat-based agent interaction in domains such as IoT, edge computing, and home automation.
Waldiez is an Autonomous agents & workflows product. It focuses on simplifying the orchestration and deployment of multi-agent AI systems for real-world applications. It is built as an open-source project for AI engineers and developers. Waldiez is open source under the Apache-2.0 license. The product ships for the web and the command line, and it can be self-hosted.
It is developed by Waldiez contributors, and the product first shipped in 2024. Development happens publicly on GitHub with 129 stars and 4 commits in the last 90 days. Key capabilities include visual workflow builder, multi-agent orchestration, and edge deployment.
Latest indexed changes and source events
Other apps tracked under the same category.
