I built BHive: a multi-agent framework for Gemini/OpenAI/Anthropic/Ollama. Tear it apart.

A developer built BHive, an open-source TypeScript multi-agent framework that lets agents delegate tasks, call tools, and run against any LLM provider — Gemini, OpenAI, Anthropic, or local Ollama — through a shared LLMAdapter interface. The project includes a ToolCallingParser that normalizes tool-call formats across providers and a ToolCallValidator with injection guards, allowlists, and size limits, and ships with 299 passing tests at roughly 98% coverage. The developer is soliciting technical design feedback before investing further time.

I've been building this for two weeks and want honest technical feedback before I invest more time. Bhive is a multi-agent framework in TypeScript. Agents "Bees" can delegate tasks to each other, call tools, and it works with any LLM provider — Gemini, OpenAI, Anthropic, or local Ollama — through the same code. LLMAdapter interface, with a ToolCallingParser that normalizes tool-call formats across providers. Good pattern, or overengineered for what it does? ToolCallValidator : injection guards, allowlists, size limits — anything missing? createDelegationTool makes sense as an abstraction Repo: https://github.com/dcooperdev/bhive-core https://github.com/dcooperdev/bhive-core Tests: 299 passing, ~98% coverage. But test coverage isn't the same as "this is well-designed" — that's what I actually want checked.