llama-cpp-agent

llama-cpp-agent is a Python framework for interacting with LLMs running via llama.cpp. It provides a unified interface for chat, structured function calls, and JSON-formatted output — including models not explicitly fine-tuned for function calling. Developers can define tools and callable functions that the agent invokes directly, making it practical for building local agentic workflows without cloud dependencies.

llama-cpp-agent is currently grouped under LLM Infra, which makes it easier to evaluate through workflow fit instead of isolated features alone. Based on the available data, it leans most heavily toward Structured function calls for models running via llama.cpp and Building local agentic pipelines with open-source LLMs. It also shows measurable community traction with 650 GitHub stars.