Open-source Mac tool to inspect LLM cost and agent runs
context-scope is an open-source tool for Mac that shows how an LLM uses tokens. It also helps inspect tool calls and agent execution. This can help people building AI agents find wasted cost and confusing steps.
Key points
- It runs locally on a Mac, so work can stay closer to your machine.
- It shows token use, which helps spot where AI costs grow.
- It lets you inspect tool calls and agent execution to find where a run failed.
Quick term guide
- context
- The information an AI uses to understand your request, such as files, notes, and past messages.
- open-source
- Software whose code is shared publicly so others can inspect, use, or change it.
- tool calls
- Times when an AI system uses another function, such as search or file access.
- tool call
- One time an AI agent uses a tool, such as search, calculation, or file reading.
- agent execution
- The step-by-step work an AI agent does to complete a goal.
- AI agents
- AI agents are AI tools that can carry out steps toward a goal, not just answer once.
- AI agent
- An AI program that can inspect information and suggest what to do next.
- locally
- Running on your own computer or server instead of a remote company server.