Tether AI introduces BotPsy, a sub-billion-parameter agentic language model

tether ai research has introduced botpsy, a 0.8b-parameter agentic language model built on top of qwen3.5-0.8b. botpsy is designed for function calling and agentic workflows, suitable for on-device deployment. it outperforms models up to 1.2b parameters on tool-use and agentic benchmarks, including qwen3.5-2b-think, a model 2.5 times its size. botpsy provides exceptional instruction-following reliability and efficiency while keeping user data private, making it suitable for tasks of low to medium difficulty.