AgentRelay context shuttle

Losslessly shuttle context between ChatGPT web and coding agents

Problem

A developer complained that chatgpt.com often feels smarter than coding agents, forcing manual copy-paste of context back and forth between web and agent, which is slow. The top-tier subscription also has much weaker tool calling than agents. Another user noted quotas are scattered across AI tools and costs are hard to control.

Solution

A browser extension plus local CLI: one click exports the current conversation, code snippets, and project context into a structured 'dossier', then injects it into an agent or another AI tool. It logs diffs and consumption per transfer, letting users jump between 'smarter' and 'more capable' models without losing context.

Users

Developers using both web LLMs and coding agents, heavy AI users

MVP

One-click export of current chat/selected code into a structured dossier; import dossier into CLI or agent; context diff comparison; simple token usage log

Revenue

Free base features + premium subscription (multi-dossier, team sharing, usage stats) at $5–10/month

Why now

Coding agents and web LLMs each have gaps, forcing manual shuttling that won't disappear soon, making it a good niche for a small tool.