contextmeter

A live meter for your LLM's context window — see exactly what's filling it.

contextmeter is a tiny local proxy + terminal HUD. Point your LLM app at it and watch, in real time, how your context window fills up — broken down by system prompt, tool definitions, chat history, and tool outputs. It makes the invisible "tool tax" obvious: "34% of your window is tool schemas you never call."

It auto-detects the request format per call, so it works with any OpenAI-compatible API, Anthropic, and Google Gemini out of the box — no code changes, just a base-URL swap. Responses are streamed straight through.

Works with

Anything that speaks the OpenAI chat format — OpenAI, OpenRouter, Groq, Together, Mistral, DeepSeek, Fireworks, and local servers like Ollama, vLLM, and LM Studio — plus Anthropic (Claude) and Google Gemini. contextmeter figures out which format each request uses on its own (Gemini's model is even read from the request URL).

Install

uv pip install contextmeter

Use

Start the meter (provider is auto-detected; defaults to forwarding to OpenAI):

contextmeter

Then point your app's base URL at http://localhost:8765. To forward somewhere else (Anthropic, a local server, OpenRouter, …), just set --upstream:

contextmeter --upstream https://api.anthropic.com
contextmeter --upstream http://localhost:11434

--provider is optional — pass openai or anthropic only if you want to pin the format instead of letting it auto-detect.

Note: pass the host root as --upstream, not the /v1 endpoint. Your LLM client already appends the path (e.g. /v1/chat/completions), so use http://localhost:11434 — not http://localhost:11434/v1 (which would double the path to /v1/v1/...).

Why

Most developers have no idea what's eating their context window. Tool definitions alone can consume 40–60% before the first message. contextmeter shows you, live, in your terminal.

Status

Supports OpenAI-compatible, Anthropic, and Google Gemini request analysis with automatic per-request provider detection, streaming pass-through, and counting of the model's emitted tool_calls/tool_use payloads. Token counts are approximate (tiktoken-based; Anthropic and Gemini are approximated).

Roadmap: Python wrapper entry point (no proxy); pricing/limits auto-refresh; richer Textual UI.