OmniContext — LLM Context & Bloat Monitor 作者： Shrihari006

OmniContext is a lightweight browser extension that monitors Large Language Model (LLM) context window capacity in real time. Long conversations can cause context bloat, degrading response quality and increasing latency. OmniContext provides an interactive overlay to track token usage and maintain optimal performance across AI chat platforms.

Key Features:

Real-Time Token Tracking: Automatically detects the active model (Gemini, Claude, ChatGPT, DeepSeek, Kimi, Qwen) and tracks token consumption against official context limits.
Context Bloat Score: Calculates a health score based on total tokens, message count, and code density.
Context Summary Generator: Injects a structured summary prompt with one click to transition long conversations into fresh sessions.
Interactive HUD: Moveable, resizable, and collapsible overlay interface with global ON/OFF controls.
Private and Local: Runs entirely in the browser. No data collection, telemetry, or external API calls.