Nessie

About

Nessie is a context layer for AI-native work. It ingests all available history from the AI conversations and local sources you already use, including ChatGPT, Claude, Codex, Cursor, and 20+ more tools, plus meetings and files. After you connect an integration once, Nessie backfills its history and keeps new sessions, meetings, and files flowing in, with no copy-pasting and no browser extension. It serves that context back to your people and their agents as searchable, permissioned material grounded in the original sources.

Agents access Nessie directly through the CLI, MCP, and skills. They can search past sessions, read full transcripts, and pick up a teammate's work with its decisions and blockers intact. An agent sees exactly what the person running it can see. Every share has an owner, a scope, and an audience, and context moves only when someone decides it should. You can share a single session, a repository, a whole integration, or a context, with access granted to people, teams, or admins. Nessie is private by default, with Privacy Mode, which the website says no one at Nessie can read and which is never used to train models. Your library starts on your machine, Cloud Sync is opt-in for teams, MCP, and remote agents, and the whole system can run on your own infrastructure.

Nessie is not another AI chat app. You keep using the tools you already work in, and Nessie sits above them as the shared memory and context layer. The website offers a Mac download, a demo booking, and an emailed download link.