Summary
Contextberg launched as a local memory app that records screens, inputs, browser activity, and agent transcripts, then serves that context back to agents such as Claude Code and Cursor through a built-in MCP server. It also builds activity, daily, and long-term memory layers while keeping data on the local machine.
What changed
Contextberg introduced a local-first MCP memory layer that captures work activity in the background and makes it queryable by compatible coding agents.
Why it matters
Persistent memory is becoming a separate product category around coding agents. Contextberg stands out by combining background capture with an MCP delivery layer, which turns passive work history into reusable context instead of relying on users to manually restate prior decisions.
Evidence excerpt
Contextberg says it records screens, inputs, browser activity, and agent conversations, serves them to coding agents via MCP, and writes that activity into daily and long-term memory while keeping data local.