There’s something deeply satisfying about seeing a project that goes against every trend in modern software. While most AI assistants ship as multi-gigabyte Electron apps or Python monoliths that chew through RAM like it’s nothing, [NullClaw](https://github.com/nullclaw/nullclaw) just showed up with a 678KB static binary and said “hold my beer.” Written entirely in Zig — yes,… Continue reading

There’s a question floating around dev circles that nobody has a clean answer to yet: when AI writes your code, should there be a record of that conversation baked into the commit? [Memento](https://github.com/mandel-macaque/memento), a new Git extension by Manuel de la Pena, takes a strong stance — yes, absolutely, and here’s how. The idea is… Continue reading

There’s something deeply satisfying about running an AI model on your phone with zero internet connection. No API calls, no cloud latency, no wondering what happens to your data. That’s exactly what [Google AI Edge Gallery](https://developers.googleblog.com/on-device-function-calling-in-google-ai-edge-gallery/) delivers, and the latest update makes it way more interesting than a simple on-device chatbot. The app landed on… Continue reading

Here’s a question that’s been bugging me lately: if someone asks ChatGPT “what’s the best tool for X” and your product doesn’t show up, would you even know? Probably not. And that’s exactly the problem [Geostorm.ai](https://github.com/geostorm-ai/geostorm) is trying to solve. Geostorm is an open-source monitoring tool that periodically queries major AI models — GPT, Claude,… Continue reading

There’s a new open-source project making serious noise in the agent space, and honestly, it deserves the attention. [OpenFang](https://github.com/RightNow-AI/openfang) launched on February 24th and racked up over 7,000 GitHub stars in under a week. By March 1st, it was sitting at [#2 on Trendshift](https://trendshift.io/) and pulling [143 upvotes on Product Hunt](https://www.producthunt.com/) on the same day.… Continue reading

Anthropic just made it embarrassingly easy to leave ChatGPT behind. On March 1st, they quietly dropped [Claude Import Memory](https://claude.com/import-memory), a feature that lets you transfer all those personalized memories your current AI has built up about you — your name, your job, your coding preferences, the way you like your responses structured — straight into… Continue reading

There’s something almost absurd about the story behind [Xmloxide](https://github.com/jonwiggins/xmloxide). A developer pointed Claude Code at libxml2’s test suite and basically said “make this pass.” Three hours later, the agent had produced a full Rust reimplementation of one of the most important XML libraries ever written. And here’s the kicker — it passes every single test.… Continue reading

If you’ve spent any real time with Claude Code, you know the pain. You’re deep into a coding session, everything’s flowing, and then — context degradation hits. The conversation starts forgetting things you told it ten minutes ago. Your 200K context window got eaten alive by Playwright snapshots, API responses, and log files you never… Continue reading

I’ve been staring at [MicroGPT](https://karpathy.github.io/2026/02/12/microgpt/) for the past week and I still can’t fully wrap my head around the fact that this thing exists. Andrej Karpathy — yes, the former head of Tesla AI and OpenAI co-founder — sat down and wrote a complete, working GPT in 243 lines of pure Python. No PyTorch. No… Continue reading

If you’ve been running quantized models locally, you know the drill — smaller file sizes come at the cost of accuracy. You pick a quant level, cross your fingers, and hope the output doesn’t turn into gibberish. [Unsloth Dynamic 2.0](https://unsloth.ai/blog/dynamic-v2) throws that one-size-fits-all approach out the window, and honestly, it’s about time someone did. The… Continue reading