Hey HN! I've been working on cppbolt, a lightweight C++ to WebAssembly compiler written in Rust. The idea was to build something that can compile and run C++ directly in the browser without downloading a massive LLVM/Clang toolchain. Unlike projects that bundle LLVM/Clang and can require 100+ MB of compiler assets, cppbolt's compiler payload is around 1 MB. It compiles a supported subset of C++17 directly to standard WebAssembly binaries. Some things it supports: - Classes, inheritance, virtual
Hi HN! I'm Luke from Kino ( https://kino.ai ). Kino lets you make great videos with your agents and your teammates. Storage of footage and assets, a rich video editor, and review links for teammates are all bundled into one. Your colleagues and Codex / Claude Code can work on the same timeline with review notes and footage all in one place. See a basic overview at https://kino.ai/walkthrough-video and our launch video (made entirely with Kino!) at https://kino.ai/launch-video Opus 5.5 can edit v
Sequoia is consolidating into a smaller, Bay Area–centered firm, shutting down the programs and offices it built during a 20-year expansion while announcing roughly $10 billion in new funds.
Hey guys, I built Renor, one memory for all your agents, we got good results in benchmarks using less tokens. I built this because I was annoyed that my agents kept forgetting what I said and my existing solutions weren't good enough. It works by using a ledger of markdown that you can export.
My brother and I run a 2-person lab that trains our own generative video models from scratch. The ultimate goal is a set of creative tools that make it easier for anyone to make animation. Video models today are too slow/expensive and lack sufficient controls. Creativity is an iterative process. You make, you tweak, you get better. In our opinion, they're not usable yet for storytelling. When we set out to build Linum v3 (our next video model) earlier this year, the primary goal was to bring the
大家好，我做了一个复古像素风的无尽跑酷游戏 Dino ，现在在 Google Play 封闭测试阶段，需要至少 12 位测试者连续参与 14 天才能申请正式发布。 游戏特点： 触屏操作，也可选声音控制和头部动作控制（均在本地处理） 多种恐龙皮肤、会变化的场景 无广告、无内购、无需注册账号 参与方式（需要 Google 账号并能访问 Google Play ）： 加入 Google 群组： https://groups.google.com/g/dino-testers 打开测试链接，点“成为测试人员”： https://play.google.com/apps/testing/com.homyit.studio.dino 从 Google Play 安装，并保持安装 14 天（偶尔打开玩玩即可） 也欢迎互测：你的应用需要测试者的话，评论里留下链接，我也会帮忙。有任何问题或建议都可以直接回复，谢谢！
最近做了个有点不一样的逆向工程 Agent 。想解决的其实是个很实际的问题：逆向任务一复杂，AI 很容易跑偏，或者分析到一半就说自己搞定了。目前基于强化学习牵引所以目前支持 WEB 、PE 、ELF 、APK 、固件等方向，可以一边学习一边分析，也会把做过的方法和结果沉淀下来，后续任务能继续积累经验。项目还在迭代，欢迎对 AI 逆向感兴趣的朋友试试，也欢迎直接拿真实样本来交流和 star 。GitHub： https://github.com/amd2g2zz/kunglao-agent
Release: datasette-llm 0.1a10 Fixes a bug that affected my agent.datasette.io demo site, where the set of available LLM models was not correctly restricted to just those in the configuration. Tags: datasette , llm
Hi HN, I'm a long-time Superhuman user, and a few weeks ago I cloned it as a native Mac app. It's keyboard-first, with split inboxes, reminders, and a built-in calendar. It's local-first, including the AI features that use local models shipped in macOS 27, with the option to use Claude/Codex subscriptions. It's extremely configurable, even down to the search weights, and comes packed with CLI/MCP if you want to use it with an agent. This is my daily driver for email, but it's by no means a "