What the product actually does

NEXO Brain is not only a memory plugin. It is a local cognitive runtime that gives multiple clients the same brain, keeps operational state durable, and exposes enough surface area to be audited instead of hand-waved.

Shared brain Durable workflows Self-healing runtime Operator control
Shared brain Claude Code, Codex, Claude Desktop, and other MCP-capable surfaces can all point at the same local runtime.
Memory + state Persistent memory, followups, learnings, reminders, diaries, recent-context recovery, and structured runtime evidence.
Operational discipline Protocol tasks, release-readiness checks, startup preflight, doctor diagnostics, and update-safe migrations.

Shared brain across clients

One runtime, one local brain, multiple clients. Context and operator state survive when work moves from Claude Code to Codex or to any MCP surface wired into the same runtime.

Persistent memory that is inspectable

NEXO stores memory locally, can search it semantically, and keeps enough operational evidence that the product claim can be audited instead of trusted blindly.

Durable workflows

Tasks, checkpoints, closeout evidence, reminders, and followups let long-running work survive compaction, restarts, and overnight analysis.

Operator-facing controls

Preferences, automations, email accounts, model-quality tiers, and support surfaces are becoming product controls instead of local tribal knowledge.

Self-healing runtime

nexo doctor, startup preflight, fail-closed checks, runtime audits, and guarded updates reduce silent drift and make failures diagnosable.

Public proof surface

Website, docs, changelog, scorecards, blog, and release validators aim to describe the product as it really exists, not as a stale narrative.

Use the route that matches the question