OmniContext
Local Git Context & Handoff Bridge
Built a local dashboard and MCP bridge for sharing Git context between AI coding assistants.
Context
OmniContext is a local handoff tool for AI coding assistants. The CLI starts a foreground Next.js dashboard that reads Git state on initial load or manual refresh. A separate MCP server exposes context://current. Its task tools use an in-memory demonstration list, not persistent session tracking.
The problem
AI coding assistants operate in silos and often have usage limits. When a developer hits a limit in one tool (like Cursor) and needs to switch to another (like Claude Web), they lose all their context—active files, Git diffs, and current tasks. The challenge was building a universal bridge that captures this state and ports it seamlessly across different AI environments.
How I built it
Built a global Node.js CLI that launches a foreground local dashboard for reading Git state and uncommitted changes
Created a Next.js dashboard that formats branch, files, full diff, architecture, and manually supplied conversation into a Markdown handoff prompt
Implemented a native Model Context Protocol (MCP) server for advanced IDE integration
Exposed the context://current resource and demonstration task tools; task changes are in-memory and do not persist across server restarts
Why these choices
MCP Server Integration
A native MCP server lets compatible IDEs read project context through a resource instead of requiring a pasted handoff prompt. The MCP server is separate from the dashboard process.
Explicit Markdown Handoff
The dashboard formats the full diff and supplied context without compression or a token-budget guarantee. Developers should review and trim large handoffs to fit the receiving model.