whiteducksoftware/flock

Flock is a Python-based framework for building and orchestrating multi-agent AI workflows. It provides a modular architecture for defining agents, managing their execution via a central orchestrator, and handling artifact-based communication. The system supports diverse LLM backends, including OpenAI, Azure, and local models, while offering extensible components for safety, scheduling, and server-side logic. It also includes a React-based dashboard for real-time monitoring and control.

This period focused on establishing the core Flock framework architecture, introducing modular components for agents, orchestrators, and servers, alongside a new React-based dashboard for real-time monitoring. The work included implementing the Model Context Protocol (MCP) integration, adding scheduling and semantic subscription capabilities, and providing extensive examples and test coverage to validate the new system.

68 changes

This period focused on integrating external compute and storage backends, specifically adding support for the OpenClaw runtime and Dapr state stores. The work included implementing the necessary modules, configuration models, and streaming support, alongside comprehensive integration and unit tests to ensure reliability.

6 changes

whiteducksoftware/flock was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point the surveyor at a repository you know and see whether you agree with it.