MCP core for an LLM assistant
Backend core for an LLM assistant with plugin execution, hot reload, tool chains, and explicit context handoff.
Plugins can change without restarting the whole assistant idea.
The useful part is predictable execution, not just model access.
AI Tooling Developer
When an assistant grows beyond a demo, plugins and tool calls become hard to evolve without breaking the whole runtime.
Built a FastAPI execution core with plugin lifecycle management, hot reload, cascading tool calls, and a CLI client with execution history.
New tools can be added without rewriting the assistant core, and tool execution is easier to inspect.
- Implemented plugin hot reload without restarting the core process.
- Built explicit context handoff between chained tools.
- Separated runtime responsibilities from plugin responsibilities.
- AI tooling becomes useful when execution behavior is predictable.
- A clean plugin boundary matters more than the number of models connected.
More projects
nnzen model catalog
A live LLM catalog that collects model data, normalizes it, and makes model comparison faster.
FastAPI backend performance cleanup
Optimization of a FastAPI API path: async I/O, connection reuse, Redis cache, request validation, metrics, and removal of serial bottlenecks.