Updates, insights, and deep dives from the MemClaw team.
POV pieces, benchmarks, and where agent memory is going.
How MemClaw is built, the primitives that power it, what shipped.
Integrations, tutorials, and customer stories.
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 →POV pieces, benchmarks, and where agent memory is going.
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.
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.
The Karpathy Loop proved autonomous AI research works. But scaling it to agent fleets needs governed shared memory — persistent, structured, and self-improving.
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.
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.
How MemClaw is built, the primitives that power it, what shipped.
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.
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.
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.
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.
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.
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.
Integrations, tutorials, and customer stories.
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.
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.
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.
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.
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.
Paste one MCP config block and Cursor remembers across sessions, projects, and teammates. Personal today, governed fleet infrastructure tomorrow.
One CLI command gives Claude Code persistent memory across sessions, projects, and machines. Personal today, governed fleet infrastructure tomorrow.