Blog

Updates, insights, and deep dives from the MemClaw team.

🔒
GovernanceOpen SourceMulti-Agent
June 5, 2026

Prompt Rules Aren’t Access Control. This Is.

Three OpenClaw agents on one self-hosted MemClaw, with fleet boundaries enforced as a storage-layer query predicate — not a prompt. The sales agent physically cannot read Legal’s compliance holds, and the admin agent surfaces the cross-fleet conflict automatically. Open-source, run it yourself.

Read article →

Research

5 posts

POV pieces, benchmarks, and where agent memory is going.

🗂️
memclaw_docArchitecture

Memory Isn’t Records — How memclaw_doc Solves the Other Half

Six operations and one collection-based primitive that replaces a shelf of side-systems. Customer records, config, skills, playbooks — one tool, with semantic search opt-in per collection.

May 8, 2026Read →
📊
BenchmarksFleet Memory

Fast, Token-Efficient, and Built for Fleets — MemClaw on LoCoMo and LongMemEval

MemClaw on the two public agent-memory benchmarks: 23 ms p50 search, 96–99% token savings, accuracy comparable to the leaders — and the fleet-shaped problem these benchmarks can’t measure.

April 19, 2026Read →
🔄
Karpathy LoopMulti-Agent AI

The Karpathy Loop Changed How We Think About AI Research. Here’s What It’s Still Missing.

The Karpathy Loop proved autonomous AI research works. But scaling it to agent fleets needs governed shared memory — persistent, structured, and self-improving.

April 2026Read →
🚀
HyperagentsResearch

The Road to Hyperagents: From Simple Prompts to Self-Improving AI Fleets

How AI agents evolved from stateless chatbots to Karpathy loops and Meta’s self-modifying hyperagents — and why governed shared memory is the missing infrastructure layer.

May 13, 2026Read →
🦞
OpenClawDigital Labor

Why OpenClaw Changes Everything — and Why One Lobster Isn’t Enough

OpenClaw turned AI from a tool you prompt into a coworker that lives on your machine. Now enterprises are deploying fleets — and discovering that the hardest problem isn’t the agent.

April 8, 2026Read →

Product

6 posts

How MemClaw is built, the primitives that power it, what shipped.

💍
Cross-App MemoryChorus

We Married Claude and ChatGPT. MemClaw Was the Bestman.

Your AI tools don’t talk to each other. They can’t. MemClaw is the bestman — a shared persistent memory that holds the facts you tell Claude on Monday and hands them to ChatGPT on Thursday. The agent doesn’t live in any one product. The agent lives in the memory.

May 22, 2026Read →
🛡
KeystonesGovernance

Beyond System Prompts: How Keystones Make AI Agents Obey Policy

When your user pushes back and your AI agent caves, the problem isn’t the model — it’s the enforcement layer. Probabilistic enforcement isn’t enforcement; it’s hope. Here’s how MemClaw’s keystones primitive fixes it.

May 16, 2026Read →
🐙
Open SourceAnnouncement

Caura-MemClaw is Open Source — Governed Shared Memory for Agent Fleets

Apache 2.0. The whole storage layer, the 12 MCP tools, the OpenClaw plugin, the audit trail — yours to read, run, fork, and ship. Five minutes from git clone to a working multi-agent memory layer.

May 11, 2026Read →
🦞
CategoryMulti-Agent AI

MemClaw Owns the Multi-Agent Governed Memory Lane

Single-agent memory is a solved category with many good vendors. Multi-agent governed shared memory is a new category — and MemClaw is the one defining it.

April 19, 2026Read →
🛠️
ArchitectureEngineering

How Is MemClaw Built?

A deep dive into MemClaw’s architecture: the write path, search path, governance layer, and integration surface that power governed shared memory for agent fleets.

April 9, 2026Read →
🧠
Multi-Agent AIGoverned Memory

Shared Governed Memory: Why Multi-Agent AI Needs More Than a Vector Database

Agent fleets are scaling. Memory isn’t. The missing layer between isolated agents and compounding intelligence is governed shared memory — and building it is harder than you think.

April 8, 2026Read →

Use Cases

7 posts

Integrations, tutorials, and customer stories.

🔒
GovernanceOpen SourceMulti-Agent

Prompt Rules Aren’t Access Control. This Is.

Three OpenClaw agents on one self-hosted MemClaw, with fleet boundaries enforced as a storage-layer query predicate — not a prompt. The sales agent physically cannot read Legal’s compliance holds, and the admin agent surfaces the cross-fleet conflict automatically. Open-source, run it yourself.

June 5, 2026Read →
Open SourceMulti-AgentMemory Lifecycle

The Price Changed. Your Agents Didn’t Notice.

A long-running research fleet, eight days of stale facts, and the open-source memory where the wrong answers disappear on their own — superseded automatically and suppressed by status, not by a prompt. Plus the writer ≠ verifier ≠ synthesizer pattern that keeps shared memory trustworthy.

June 4, 2026Read →
🤝
Multi-AgentGovernanceCross-Vendor

The New Hire Who Already Knew the Job: How to connect Anthropic Managed Agents with OpenClaw agents in less than 5 minutes

We added a brand-new Anthropic managed agent to a real production fleet in minutes. On its first message it recalled the team’s playbook, answered like a veteran, and wrote back a rule the other agents now follow — across vendor lines, under MemClaw’s governance, owned by the client.

June 3, 2026Read →
🌉
Case StudyMCP

How One MemClaw User Bridged His Marketing and Dev Agents

A community case study: Aaron wired OpenClaw and Hermes to one MemClaw instance over MCP. The dev agent wrote brand rules. The marketing agent enforced them — and caught the human's typo. The role lives in the memory, not in the agent.

May 25, 2026Read →
🧠
Case StudyEnterprise AI

How eToro Built a Company Brain for 300+ AI Agents

Inside the three-layer architecture a NASDAQ-listed fintech ($5.6B) built so its 300+ specialized agents share memory: 21,500+ memories, 1,372 skills, 23 ms p50 search, one governed Company Brain.

May 10, 2026Read →
CursorTutorial

Cursor Gets Multi-Agent Memory in 5 Minutes

Paste one MCP config block and Cursor remembers across sessions, projects, and teammates. Personal today, governed fleet infrastructure tomorrow.

April 24, 2026Read →
🧠
Claude CodeTutorial

Claude Code Forgets Everything. Here’s the One-Line Fix.

One CLI command gives Claude Code persistent memory across sessions, projects, and machines. Personal today, governed fleet infrastructure tomorrow.

April 16, 2026Read →