ollama-llmwatch is an MIT-licensed Python package that monitors local Ollama model activity. It provides live prefill progress, estimated completion times, and tokens-per-second metrics for developers running local language models.
In the Observability & monitoring space, ollama-llmwatch takes a focused approach. It focuses on understanding the progress, completion time, and generation speed of local Ollama model runs. It is built as an open-source project for developers. ollama-llmwatch is open source under the MIT license. It runs on the command line, and it can be self-hosted.
ollama-llmwatch first shipped in 2026. Among its 4 catalogued features are live prefill progress, ETA estimates, and token speed monitoring.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do