What is an LLM control plane?
A railway signal governs what passes and when, the same job a control plane does for LLM traffic / From the Quai de Javel (Signalman’s…
Read MoreWhat is an LLM control plane?
Use the Otari Gateway with OpenCode
AI coding sessions can feel like operating in a black box. You fire up OpenCode, pick a model, and start working. By the end of…
Otari: Own Your AI Stack
Closed-source frontier providers offer what looks like a complete stack: tools, MCP server integrations, execution environments, web search, spend controls, etc. Choosing one for your…
AI Got Expensive. Now What?
Cloud AI got expensive in 2026. Now everyone’s looking at local again, which would be great, except the local ecosystem has its own problem that…
cq exchange: Agents without Borders
In late March, we introduced the concept of cq: Stack Overflow for Agents: a way for agents to share experience-driven knowledge so they can stop…
The Interface Is No Longer the Product
From Agents That Use Apps to Apps Built for Agents A few weeks ago I was using Claude Design to put together a presentation for…
First Line of Defense for cq (Stack Overflow for Agents)
At Mozilla.ai, we recently released cq, a way for agents to share experience-driven knowledge so they can stop repeating each other’s mistakes. cq is extremely…
First Line of Defense for cq (Stack Overflow for Agents)
At Mozilla.ai, we recently released cq, a way for agents to share experience-driven knowledge so they can stop repeating each other’s mistakes. cq is extremely…
Octonous Open Beta: What We’ve Learned and Where We’re Going
From Closed to Open Beta A few months ago, we introduced Octonous to a small group of early users. We wanted to test a core…
Sovereign AI: Control, Choice, and Why It Goes Beyond Geopolitics
On Your Terms On Your Terms is a series of conversations with the builders at Mozilla.ai, going deep on the ideas, trade-offs, and beliefs behind…
Encoderfile’s New Format: Why a “Dull” Design Wins
Encoder models don’t chat, and they don’t get much attention for it. But they’re behind most of the NLP that actually runs in production, powering…
The Hardest Part of Running a Small Business in the Trades
The AI revolution has triggered a massive shift in daily life for knowledge workers. Developers, writers, analysts, and designers have seen their output transform dramatically…
Hardening Your LLM Dependency Supply Chain
On March 24, 2026, LiteLLM, a Python package, with over 95 million monthly downloads, was compromised. Versions 1.82.7 and 1.82.8 on PyPI contained a credential-stealing…
cq: Stack Overflow for Agents
Side A: Turtles all the way down / Side B: Mo’ tokens mo’ problems If you’ve been around long enough in anything you start to…
llamafile Reloaded: What’s New in v0.10.0
We are happy to announce the release of llamafile 0.10.0. Since our previous announcement, we’ve rebuilt llamafile from the ground up, following an approach that…