Open Source AI and Open Weight Models: Guides and News
Open source agent frameworks and open weight models, read against the repository and the paper rather than the launch post. I install them, run them, and report what the demo proves, what it costs, and what breaks on day one.
5 posts
How to29 min readHow to Run Google's Harness2: What It Costs, What Breaks and What to Block
A step by step guide to Google Research's Harness2, with the demo run for real: install it, read its output, price a run with the 4k and 3k budget, block rubric leaks and plug in your own tasks.
How to14 min readHow to Set Up Hermes Agent and Lock Down the Defaults First
What Hermes Agent from Nous Research is, how to install it, which models it works with, how to lock it down, what it costs to run, and when to pick it over OpenClaw.
News6 min readMuse Spark Open Needs Two Mac Studios and Trails Kimi K3 at Coding
Meta released the weights for Muse Spark Open, an 816B model it says runs on two Mac Studios. The memory math, the license strings and Meta's own benchmark table tell a narrower story.
News14 min readKimi K3 Broke the Benchmarks. Almost Nothing Changes for Your AI Stack.
A breakdown of Moonshot's Kimi K3 launch, why the cheap-Chinese-model narrative gets the pricing exactly backwards, and what teams running AI agents should actually do about it this week.
Guide17 min readGoogle Just Released the Most Capable Open Source AI Agent Model. Here Is What It Means for Your Business.
Google's Gemma 4 scored 86.4% on tau2-bench for agentic tasks, a 13x jump over Gemma 3. Here is what the most capable open source AI agent model means for businesses building AI systems in 2026.