Bumblehive is an open-source agent runtime built for tool-driven loop engineering. It provides a framework for creating, testing, and running LLM-based agents that interact with tools in iterative loops. The package includes support for the Model Context Protocol (MCP) and is designed for developers building reliable AI agent systems.
bumblehive sits in PulseGate's AI & ML category. It focuses on building and iterating on reliable tool-calling agent loops without a suitable runtime framework. It is built as an open-source project for AI developers and agent engineers. The project is open source (Apache-2.0). It runs on the command line and API, and it can be self-hosted.
Behind bumblehive is wxhcore, and it first shipped in 2026. The project is developed in the open on GitHub with 176 commits in the last 90 days. Key capabilities include Agent Runtime, Tool Calling, and Loop Engineering. It exposes integrations via an MCP server and a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match