Tether AI Research releases BotPsy, a 0.8B-parameter on-device agent model

Tether AI Research has published BotPsy, a 0.8B-parameter language model built on Qwen3.5-0.8B and post-trained for function calling and agentic workflows that run locally. It is pitched as a personal assistant that calls tools across web search, travel, commerce and finance, files and documents, calendar, and email. The team reports it roughly doubles its base model's scores on three tool-use benchmarks and beats Qwen3.5-2B-Think, a model 2.5 times larger, on five of six benchmarks it tested; it trails on Claw-Eval. Weights are open under Apache 2.0 for research and educational use, in bf16, Q8 and Q4 precision as safetensors and GGUF files for the QVAC SDK and llama.cpp. The team states it is not intended for high-stakes use.