<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>OpenClawMU — The multi-tenant AI gateway your platform can actually share</title><description>OpenClawMU is the multi-tenant fork of OpenClaw — a self-hosted AI gateway across WhatsApp, Telegram, Slack, Discord, Signal, iMessage, Teams, Matrix and more. Add tenant isolation, sandboxed agents, per-tenant tokens and quotas, web terminals, and S3 backup. Apache-2.0, self-hosted, no SaaS lock-in.</description><link>https://openclawmu.neullabs.com/</link><language>en-us</language><generator>Astro</generator><item><title>What is a multi-tenant AI gateway? The architecture, explained.</title><link>https://openclawmu.neullabs.com/blog/multi-tenant-ai-gateway-explained/</link><guid isPermaLink="true">https://openclawmu.neullabs.com/blog/multi-tenant-ai-gateway-explained/</guid><description>A multi-tenant AI gateway is the layer between your messaging channels and your LLM that isolates per-customer state. Here&apos;s how the pattern works, why it matters now, and what a defensible implementation looks like.</description><pubDate>Wed, 03 Jun 2026 00:00:00 GMT</pubDate><category>multi-tenant</category><category>AI gateway</category><category>architecture</category><category>infrastructure</category><category>LLM</category></item><item><title>Self-hosted WhatsApp bot platform: the open-source playbook</title><link>https://openclawmu.neullabs.com/blog/self-hosted-whatsapp-bot-platform/</link><guid isPermaLink="true">https://openclawmu.neullabs.com/blog/self-hosted-whatsapp-bot-platform/</guid><description>Run a multi-tenant WhatsApp bot platform on your own infra without the WhatsApp Business API contract. Open-source, BYO-LLM, with per-customer isolation and cost tracking. Here&apos;s the architecture.</description><pubDate>Tue, 02 Jun 2026 00:00:00 GMT</pubDate><category>WhatsApp</category><category>bot platform</category><category>self-hosted</category><category>Baileys</category><category>open source</category></item><item><title>OpenClaw vs OpenClawMU: when to fork from single-user to multi-tenant</title><link>https://openclawmu.neullabs.com/blog/openclaw-vs-openclawmu/</link><guid isPermaLink="true">https://openclawmu.neullabs.com/blog/openclaw-vs-openclawmu/</guid><description>OpenClaw is a brilliant single-user AI gateway. OpenClawMU is the multi-tenant fork. Here&apos;s exactly what differs, when the fork is worth it, and how to migrate cleanly without losing state.</description><pubDate>Mon, 01 Jun 2026 00:00:00 GMT</pubDate><category>openclaw</category><category>openclawmu</category><category>multi-tenant</category><category>fork</category><category>migration</category></item><item><title>Tenant isolation for LLM agents: the patterns that actually hold up</title><link>https://openclawmu.neullabs.com/blog/tenant-isolation-for-llm-agents/</link><guid isPermaLink="true">https://openclawmu.neullabs.com/blog/tenant-isolation-for-llm-agents/</guid><description>Isolating LLM agents per tenant is harder than adding a tenant_id column. Here are the patterns that survive contact with adversarial users, leaky tools, and the inevitable refactor.</description><pubDate>Fri, 29 May 2026 00:00:00 GMT</pubDate><category>tenant isolation</category><category>LLM agents</category><category>security</category><category>multi-tenant</category><category>architecture</category></item><item><title>Bubblewrap vs Docker: choosing a sandbox for AI agent tool calls</title><link>https://openclawmu.neullabs.com/blog/bubblewrap-vs-docker-sandbox-for-agents/</link><guid isPermaLink="true">https://openclawmu.neullabs.com/blog/bubblewrap-vs-docker-sandbox-for-agents/</guid><description>Sandboxing AI-agent tool calls is mandatory. Bubblewrap and Docker are both viable; here&apos;s the trade-off matrix on cold start, isolation surface, OS support, and operational complexity — and when each one wins.</description><pubDate>Tue, 26 May 2026 00:00:00 GMT</pubDate><category>sandbox</category><category>bubblewrap</category><category>docker</category><category>ai agents</category><category>security</category></item><item><title>Per-tenant LLM cost accounting: meter, attribute, charge</title><link>https://openclawmu.neullabs.com/blog/billing-per-tenant-llm-usage/</link><guid isPermaLink="true">https://openclawmu.neullabs.com/blog/billing-per-tenant-llm-usage/</guid><description>If you&apos;re charging customers for an AI product, you need per-tenant token tracking. Here&apos;s the data model, the rate-card pattern, and the integration with Stripe Billing or your invoicing of choice.</description><pubDate>Fri, 22 May 2026 00:00:00 GMT</pubDate><category>billing</category><category>LLM cost</category><category>per-tenant</category><category>Stripe</category><category>metering</category></item><item><title>From personal Telegram bot to multi-customer bot platform: field notes</title><link>https://openclawmu.neullabs.com/blog/from-personal-bot-to-bot-platform/</link><guid isPermaLink="true">https://openclawmu.neullabs.com/blog/from-personal-bot-to-bot-platform/</guid><description>Field notes on graduating a single-user Telegram bot into a multi-tenant SaaS. The architectural choices that survived, the mistakes that didn&apos;t, and the migration timeline.</description><pubDate>Mon, 18 May 2026 00:00:00 GMT</pubDate><category>field notes</category><category>telegram</category><category>multi-tenant</category><category>bot platform</category><category>migration</category></item></channel></rss>