Shifting between LLMs for their unique strengths is standard workflow now, but managing the data state between browser tabs is an absolute nightmare. Here is how I used the Plasmo framework to build a lightweight, local-first context compiler called ContextOS.
Framework: Plasmo (React + TypeScript + Chrome MV3).
Storage: chrome.storage.local handles the entire project matrix. No external databases.
The Parsing Loop: Users input a free Gemini API key (BYOK). When a user hits ✨ Sync to Project Context, a background worker handles the raw text payload, processes it structurally, and commits it into dynamically named local state blocks.
The hardest part was getting clean injection mechanics across wildly different DOM layouts (ChatGPT, Grok, Claude, etc.). I implemented weightless content scripts that target the active webpage text areas, formatting the project's modular buckets into clean, hierarchical Markdown right before injection.
Check out the source listing or download it free on the Chrome Web Store if you want to optimize your multi-AI dev loops!
check out on Chrome Web Store:
Faisal Ahmed Rony
Founder of Total InfoHub | Tech Blogger & SEO Specialist
This is a crucial enhancement for Spring AI. Currently, building advanced observability or compliance logging around tools is quite challenging because advisors lose the execution context during concurrent tool calls. Having a structured way—like a contextual map or a token shared during the execution chain—to link advisors back to the specific tool metadata would make enterprise-level AI orchestration much more robust. Looking forward to seeing how this evolves!