Without an AI Coding policy that promotes transparency alongside innovation, Open Source codebases are going to struggle Remember early 2025? “Vibe coding” was a meme…

Over the last few weeks, we’ve been running a small, gated alpha of any-llm managed platform: our client-side encrypted API key vault and usage tracking service…

In October, we shipped mcpd as a “requirements.txt for agentic systems”, a way to declaratively manage your MCP servers across environments. A few weeks later,…

A Year of Building Momentum The year 2025 has been a busy one at Mozilla.ai. From hosting live demos and speaking at conferences, to releasing…

Following up on Baris Guler’s excellent exploration of browser-native AI agents using WebLLM + WASM + WebWorkers, we’re excited to present a complementary approach that…

We recently released any-llm v1.0, our SDK for building with multiple providers using a single unified interface, as well as any-llm-gateway. Today we’re expanding the…

Encoders power the parts of a system where latency, repeatability, and stable outputs aren’t optional. Yet many teams still default to autoregressive models because they’re…

A few weeks ago, we were speaking with a Principal Data Scientist leading engineering teams at Microsoft’s AI Consulting Practice, a group that works closely…

Track Usage, Set Limits, and Deploy Confidently Across Any LLM Provider Managing LLM costs and access at scale is hard. Give users unrestricted access and…

Introduction AI Agents extend large language models beyond text generation. They can call functions, access internal and external resources, perform deterministic operations, and even communicate…

One interface for every model, now production-ready The LLM ecosystem is moving fast: new models, new providers, new API formats almost every month. That’s why…

Mozilla.ai is adopting llamafile to advance open, local, privacy-first AI—and we’re inviting the community to help shape its future. TL;DR Mozilla.ai is adopting the llamafile…

Building AI agents is hard, not just because of the LLMs, but because of everything around them: tool selection, orchestration frameworks, evaluation, safety, and more.…

🤝 This is the first “guest post” in Mozilla.ai’s blog (congratulations Baris!). His experiment, built upon the ideas of Mozilla.ai’s WASM agents blueprint, extends the…

Run your agents, not your infrastructure. In agentic systems, tools and services often live in different languages, environments, and lifecycle patterns. Managing agents across development,…