The NEXO blog

Product updates, cognitive architecture notes, field reports, and comparison guides from building an AI runtime that actually remembers, self-heals, and compounds over time.

Release notes Memory architecture Competitive analysis
April 6, 2026

MCP Memory Tools Compared: A 2026 Guide for AI Agent Builders

An honest field guide to the five MCP memory tools we keep seeing in the wild — mem0, Letta, Zep, mcp-memory and NEXO Brain. Storage shape, extraction philosophy, forgetting and operational footprint, with guidance on which to pick for which agent.

Read article
April 6, 2026

NEXO 2.7.0: Engineering Loop Metrics, Release Discipline, and a More Honest Operational Brain

NEXO now measures protocol compliance, project pressure, and engineering output across weekly/monthly Deep Sleep summaries, surfaces that signal in the dashboard, and enforces release readiness inside the repo before publish.

Read article
April 5, 2026

NEXO 2.6.21: Deep Sleep Stops Repeating Itself and Starts Engineering Fixes

Deep Sleep now deduplicates followups by meaning, consolidates overlapping learnings into canonical records, flags contradictions for review, and backfills concrete engineering followups when recurring patterns imply a real fix.

Read article
April 5, 2026

NEXO 2.6.18: Codex Session Audits, Weekly Deep Sleep Memory, and Cleaner Retrieval

NEXO now persists a managed Codex MCP contract in config, audits real recent Codex sessions and Claude Desktop metadata, writes weekly/monthly Deep Sleep summaries, and makes retrieval explanations more honest.

Read article
April 5, 2026

NEXO 2.6.17: The Codex Bootstrap Hotfix Existing Installs Actually Needed

NEXO now backfills pre-existing Codex integrations during update, fixes blank bootstrap identities when operator metadata is missing, and persists that repaired client state so later syncs stay aligned.

Read article
April 5, 2026

NEXO 2.6.16: Smarter Retrieval Defaults, Stronger Codex Runtime Parity, and 60-Day Deep Sleep

NEXO now manages Codex global bootstrap and model sync, auto-enables HyDE and shallow spreading for the right queries, tracks per-memory stability and difficulty, and gives Deep Sleep a 60-day blended horizon.

Read article
April 5, 2026

NEXO 2.6.14: Bootstrap Parity, Codex-Aware Deep Sleep, and a More Real Shared Brain

NEXO now manages Claude and Codex bootstraps with a protected CORE/USER contract, explicitly starts Codex sessions as NEXO, and feeds Codex session transcripts into Deep Sleep overnight analysis.

Read article
April 4, 2026

NEXO 2.6.12 + 2.6.13: Shared Brain Across Clients, Selectable Automation, and Better Self-Healing

NEXO now gives Claude Code, Codex, and Claude Desktop the same brain, lets users choose their terminal client and automation backend, and removes a frustrating false-critical runtime edge case with managed KeepAlive recovery.

Read article
April 4, 2026

NEXO 2.6.9: Every Integration Channel Now Verified and Synchronized

Version drift across npm, OpenClaw, and ClawHub is now impossible. NEXO 2.6.9 introduces automated artifact synchronization, a full CI/CD pipeline, and hardened packaging for every distribution channel.

Read article
April 4, 2026

NEXO 2.6.7: Your Agent Can Now Contribute Back — and Build Its Own Tools

NEXO Brain 2.6.7 introduces opt-in contributor evolution that lets any installation propose improvements to the core, personal MCP plugins that survive updates, and smoother memory continuity for daily use.

Read article
April 4, 2026

How to Give Your AI Agent Persistent Memory

Every AI agent starts each conversation from zero. Here is how persistent memory works, why context windows are not enough, and how NEXO Brain solves the problem with a cognitive architecture inspired by human psychology.

Read article
April 4, 2026

The Atkinson-Shiffrin Model: Why We Built AI Memory Like Human Memory

In 1968 Atkinson and Shiffrin described how human memory flows through three stores. We applied their model to AI agents. Here is why cognitive psychology holds the key to building agents that learn over time.

Read article
April 4, 2026

Why Your AI Agent Needs to Forget: The Case for Memory Decay

Storing everything forever sounds smart until your agent drowns in irrelevant context. Memory decay is not a bug. Here is how Ebbinghaus forgetting curves keep AI memory clean, fast, and relevant.

Read article

Give your agent a mind

Open source, AGPL-3.0 licensed, and built for builders who want their AI to actually remember.