Wire Nucleus into Claude Code
Keep your CLAUDE.md and Auto Memory. Add a queryable layer that spans every repo, tool, and session, and capture the work before compaction drops it.
Add Nucleus as an MCP server (user scope)
In your terminal, add Nucleus as an MCP server at user scope so it loads in every repo, not just this one:
claude mcp add --transport http nucleus --scope user https://app.nucleus.ae/api/mcpKeep your md files exactly where they are
Do not move your CLAUDE.md or docs into Nucleus. They stay in the repo, version-controlled, auto-loading. Nucleus sits alongside them as the cross-repo, cross-tool memory they cannot be.
Capture the session before it compacts
Claude Code auto-compacts when the context window fills up: it summarizes the conversation and discards the exact code and reasoning. Before that happens, save the real transcript to Nucleus so it stays queryable.
Optional: connect your Postgres, and Claude Code builds against your real data
If you already have a database behind your app, connect your Postgres to Nucleus. Now Claude Code reasons over the real schema, table shapes, foreign keys, and key relationships while it builds, instead of guessing them from a markdown description. It reads the structure of your data, not a doc about it.
Bonus: spin up an interface from a ghost database
Have a database running quietly in the background, data preloaded but no front-end yet? Point Nucleus at it, and Claude Code can build an accurate web or mobile interface off its real structure. Nucleus reads the table relationships, the foreign keys, the stale and live key data, so what Claude Code scaffolds matches the actual database, not a guess. We do exactly this at Nucleus when we need a front-end for a silent ghost database.
Reason across everything
In any repo, prefix a request with 'use Nucleus' and Claude Code reads the layer over MCP: your past sessions, your other repos, and any source you have connected, database included.
Try these in Claude Code
Each reaches past what this repo's memory holds, to another repo, a live source, or a session that already compacted.
1. "Use Nucleus: how did we solve auth in the other service, and apply that pattern here." (cross-repo)
2. "Use Nucleus: read the actual users table before you write this query, do not guess the columns." (real data / schema)
3. "Use Nucleus: pull up what we decided about rate limiting before the session compacted last week." (pre-compaction recall)
4. "Use Nucleus: scaffold an admin UI from my Postgres, match the real foreign keys and relationships." (ghost-database build)
Auto Memory cannot answer these. It only knows this repo, and only what survived the last compaction.
Related posts
Add Nucleus to ChatGPT
ChatGPT supports custom MCP connectors. Nucleus is an MCP endpoint. So Nucleus adds in as a custom connector and becomes ChatGPT's one grounded, joined memory across every source.
Nucleus + ClickUp task flow
Wire your ClickUp tasks and docs into one reasoning layer.
Context Is the Instruction: Why Context Engineering Requires a Layer the Model Cannot Provide
Context engineering can't optimize a working-memory buffer into a knowledge store. The evidence for why enterprise AI needs a separate context layer. A technical position from Nucleus AI. The field has correctly moved from prompts to context. We argue the move is incomplete: the context window is a working-memory buffer, and a growing body of evidence shows it cannot be optimized into the persistent, verified, organization-scoped substrate that reliable enterprise AI requires. That substrate is a separate architectural layer. This is the argument, the evidence, and a controlled observation of the layer in operation.