ToolingModular·6d ago·3 min readSummaryListen 0:53
Modular: LLVM Dev Meeting 2026: Durable Infrastructure in the Agentic EraModular discussed durable infrastructure for the agentic era at LLVM Dev Meeting 2026.
News Hub
What actually shipped in agent engineering, pulled from the labs, arXiv and Hacker News.
See who we follow75 articles
ToolingModular·19d ago·3 min readSummaryListen 0:45
Modular: Modular 26.7: Opening up MAXModular released version 26.7 of MAX with expanded openness.
ToolingModular·54d ago·3 min readSummaryListen 0:47
Modular: Modular 26.6: Open compiler contributions, audio generation, and expanded model supportModular 26.6 adds open compiler contributions, audio generation, and expanded model support.
Modular: ModCon 2026: Open source, open cloud, open silicon
Modular announces ModCon 2026 focused on open source, open cloud, and open silicon.
ResearchModular·145d ago·3 min read
Modular: Modular 26.4: SOTA MoE Serving, Model Bringup via Agent Skills, Mojo 1.0 Beta 2 and MoreModular 26.4 includes state-of-the-art MoE serving and Mojo 1.0 Beta 2.
Open sourceModular·152d ago·3 min read
Modular: Day Zero: MiniMax M3 Open Weights on Modular CloudMiniMax M3 open weights model is available on Modular Cloud.
ToolingModular·153d ago·3 min read
Modular: Modverse #55: Mojo 1.0 Beta, Community Mojo Libraries, and Real-Time Patient Conversations Powered by MAXModular released Mojo 1.0 Beta, community Mojo libraries, and real-time patient conversations powered by MAX.
ToolingModular·158d ago·3 min read
Modular: Why LLM Inference Needs a New Kind of Router - Part 3Part 3 of Modular's series on why LLM inference requires a new router architecture.
ToolingModular·165d ago·3 min read
Modular: Three trends from MLSys 2026Three trends from MLSys 2026.
ToolingModular·173d ago·3 min read
Modular: Why LLM Inference Needs a New Kind of Router - Part 2Article discusses why LLM inference requires a new kind of router.
ToolingModular·175d ago·3 min read
Modular: How I built a pure Mojo app (and 10 libraries) with AI agentsDeveloper built a pure Mojo app and ten libraries using AI agents.
Also covered byModular
ToolingModular·176d ago·3 min read
Modular: Hippocratic AI partners with Modular to power flexible, high-quality inference for real-time patient conversationsHippocratic AI partners with Modular for real-time patient conversation inference.
ToolingModular·182d ago·3 min read
Modular: Inkwell: Why Your Inference Platform Matters As Much As Your ModelInkwell examines why inference platform choice matters as much as model selection.
ToolingModular·186d ago·3 min read
Modular: Why LLM Inference Needs a New Kind of Router - Part 1Modular discusses why LLM inference requires a new router design in part one of a series.
ToolingModular·187d ago·3 min read
Modular: Modular 26.3: Mojo 1.0 Beta, MAX Video Gen, and moreModular released version 26.3 featuring Mojo 1.0 Beta and MAX Video Gen.
ToolingModular·190d ago·3 min read
Modular: Modverse #54: AMD AI DevDay, New Modular Offices, and a Community That Keeps ShippingModular announced AMD AI DevDay participation, new offices, and community shipping updates.
ToolingModular·208d ago·3 min read
Modular: How Frontier Coding Agents Built a Video Diffusion Pipeline on MAXFrontier Coding Agents built a video diffusion pipeline using Modular's MAX.
ToolingModular·211d ago·3 min read
Modular: TileTensor Part 1 - Safer, More Efficient GPU KernelsTileTensor provides safer and more efficient GPU kernel implementation.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.