workingset is an MIT-licensed Python package and CLI for estimating the capacity of local LLM deployments. It provides a capacity model and live-endpoint hypothesis tests for workloads involving agentic coding, including vLLM serving scenarios.
workingset sits in PulseGate's Inference & model serving category. It focuses on estimating how many agentic-coding users a local LLM deployment can serve. workingset is an open-source project aimed at LLM infrastructure engineers and developers operating local model deployments. The project is open source (MIT). It runs on the web and the command line, and it can be self-hosted.
It is developed by Tom Vaucourt, and it first shipped in 2026. The project is developed in the open on GitHub with 277 commits in the last 90 days. Among its 6 catalogued features are capacity modeling, CLI interface, and live endpoint tests.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match