yoagent
A minimal Rust crate providing the agent loop, streaming, and tool execution needed to build an LLM agent, working with local models out of the box and seven hosted or local protocols by configuration.
yoagent is a Rust crate implementing the agent loop, tool execution, and streaming needed to run an LLM agent, deliberately narrow in scope: it ships no vector store, embedding pipeline, or task-graph orchestration layer, pointing users toward other crates for retrieval or complex orchestration instead. A bundled command-line example works immediately against a local Ollama model with no API key, sign-up, or configuration, giving a working coding agent with file read, write, and edit, shell access, and ripgrep-based search.
Swapping to a hosted provider is a matter of setting the right environment variable and provider flag, covering Groq, Google Gemini, and any OpenAI-compatible endpoint such as LM Studio, llama.cpp, or vLLM, across seven supported protocols in total. In library form, an agent is built from a small configuration object naming the provider and model, with the corresponding API key read from that provider's conventional environment variable. It is distributed through crates.io.