People of pi. The great @steipete has graced our repository with a bespoke slop PR to fix cache affinity in the OpenAI Responses provider, which should lead to better prompt caching. And the new "pi contribution model (tm)" is now live. Here's how it works: - If you send a PR, it gets autoclosed, unless you've previously been approved by a maintainer. - If you send an issue, it gets autoclosed, unless you've previously been approved by a maintainer. All auto-closed issues are triaged daily. - Issues that follow CONTRIBUTING.md and are worthwhile will be reopened. - Issues that are exceptionally well written get an "lgtmi" comment from me or @mitsuhiko, which will approve all your future issues automatically. No more auto-closing. - Issues that are well written AND offer a PR get an "lgtm" comment from me or @mitsuhiko, which will approve all your future issues and PRs automatically. No more auto-closing. I, the idiot who has to go through all the closed slop daily, mark the last issue I processed with the "last read" label. If your issue is below that and hasn't been opened, then it did not meet the quality standard. You may or may not receive a reply on why the issue was not opened, depending on my time and mood. Accounts that: - Let their agents slop a book into the issue tracker repeatedly - Otherwise behave badly will get their account blocked across all my repositories. no exceptions. not takesies backsies. I get anywhere between 30-50 issues per day. Most of them are agent garbage. This is the only way to keep me sane and ensure the issue and PR trackers have actual good signal.

We are hiring Software Engineers in Tokyo to help us scale Sakana AI’s R&D. If you’re interested in building the data pipelines and full stack infrastructure needed to push the boundaries of automated scientific discovery, we’d love to hear from you. 🗼🎌 https://t.co/E1uPJa5tIy

THIS IS CRAZY... SOMEONE BUILT WHAT HARDWARE ENGINEERS HAVE NEEDED FOR DECADES you have an idea for a hardware project. it’s been sitting in your head for weeks... you finally decide to build it and then reality hits datasheets, component hunting, spec comparisons, building a bill of materials line by line... sketching wiring diagrams… then fixing them… again writing assembly steps from scratch none of this is actually building and it takes forever someone finally fixed that they built https://t.co/LbSvaOJtLV you describe your project in plain english like you'd explain it to a friend and it generates: – a complete wiring diagram – a full bill of materials – step-by-step assembly instructions instantly the gap between idea and prototype just got a lot smaller

Let's talk parsing tables. Two days ago we launched ParseBench,the first document OCR benchmark built for AI agents. This deep dive breaks down TableRecordMatch (GTRM), our metric for evaluating complex tables the way your pipeline actually consumes them: as records keyed by column headers. https://t.co/2sq5ncGiel

AI agents are shifting how work gets done. Instead of using a single tool, professionals may soon coordinate teams of AI agents to handle complex tasks across workflows, from law to accounting. The key question is not capability, but control. In the age of AI, agency may define who is actually in charge. https://t.co/7WhjEn2TyZ @time @macfound

🔥 TODAY: Y Combinator makes history by funding startup Totalis with $500K entirely in $USDC, marking its first stablecoin funding settled on Solana. https://t.co/s6oxHlKvbd

Wall Street just entered the game. @NYSE Wired is now official partner of our @AIatAMD Developer Hackathon - covered by @theCUBE , with @furrier & @bjbaumann2014 in the room. Code meets capital. Officially. → https://t.co/uwXWQIP1sr. https://t.co/XmlrYtfctg

In order to make sure ARC-AGI-3 games were solvable by humans we tested over 450 people If a game was too hard we either revised it or tossed it completely For maximum transparency we just open sourced all the human replays for public games My favorite charts that come out of these are the Action Progression charts. It's much easier to get a feel for how efficient environment solves turn into scores

my life changed the moment an old mentor told me this: “stopping your worst habit would change your life way faster than starting your best habit… fix the leak before filling the bucket.” https://t.co/FZWZBoOxQj

@frankgoertzen Yes https://t.co/z6DHQEj5Un

Open source AI music is actually good now 🔥 Made a free demo for ACE-Step 1.5: describe any song, get it back in seconds ⤵️ https://t.co/f4PH9GLpuC

Built a multiplayer game for my kids. No server, no internet, just two iPhones syncing over Bluetooth. They loved it. They also found a logic bug. Best QA team I've ever had. Full SwiftUI tutorial → https://t.co/ZdQ9ZSqY5K https://t.co/tsoE49GtpT

No.1. Again! 🎉 Thanks for all OSS developers! MiniMax M2.7 has only 230B parameters with 10B activated, yet delivers excellent results and outstanding performance. @MiniMax_AI It is particularly well-suited for open-source agents such as @openclaw , hermes @NousResearch , and @opencode etc. Moreover, it is totally free for individual developers. We will continue to provide better models and updates to the community. @huggingface

The new @NousResearch (Hermes Agent) dashboard looks absolutely amazing Big thanks to @Zai_org for offering such an affordable coding plan with Opus-level quality — that’s honestly a game changer. It’s a bit slow at times, but for the price and capability, it’s totally worth it. Excited to see where this goes next 🔥

Hermes hands on guide: concepts, core mechanisms, and real world use cases. https://t.co/m6bTIbPOck

Hermes hands on guide: concepts, core mechanisms, and real world use cases. https://t.co/m6bTIbPOck

AI may change not just what we buy, but how prices are set. As systems begin to shop on behalf of consumers, fashion could move toward more dynamic, personalized pricing, accelerating cycles of demand, overproduction and discounting. The shift is subtle but powerful. When AI influences both sides of the transaction, pricing itself becomes part of the algorithm. https://t.co/o5c18ZZVAA @ConversationEDU @ConversationUS

@FinancialPhys https://t.co/MrGxd4skoF

@autogame_17 I knew a lot of great founders from Shanghai and you're embarrassing their legacy. You're intellectual dishonest, 弟弟: 1) Screenshot's from TODO.md, commited Jan 30 (commit bc76a032ba29edf49d0a53963f1cbb8c51866729, check yourself). Nous had this approach outlined and part of their repo before you went public in February. 2) Runtime skill discovery was already present in the repo at that commit. 3) Their self-evolve uses DSPy, the standard solution for GEPA optimizaiton in Python. Nothing extraordinary here either. 4) Multi-layered memory is a common idea that's been in OpenClaw before January. 5) I also took my time to scrape accounts who starred your repository. Average age of an account is 900 day, 64% of the accs had zero repos. These are not real accounts. Did you buy your stars? Should I plot the graph of stars too, or should I let you save your face? Please, stop embarrasing yourself.

@conceptuelx @autogame_17 @EvoMapAI Launched it two months ago, built it 5 months ago. Look from Jan 1 where all of our shit was specced tf out you absolute moron https://t.co/GrhVv6AIRU

🔥 DFlash x MLX is happening! Shoutout to @aryagm01 for the early work on this. We're building on the momentum. Native MLX support, more models (Qwen3.5), up to 4x faster. Lossless! 👉 https://t.co/wKcRoiaWZ3

Built Hermes Mini App v2.0.0. Accidentally forked the wrong repo, pushed there, then deleted it. Classic. Anyway, it’s fixed and live! 10-page React dashboard for your AI agent, right inside Telegram. Chat, status, agents, cron, logs, config, keys — mobile-first, open source. https://t.co/0wWu9nHmjO

Hermes agent is pretty useful. I see a lot of people ask what it’s good for. Using agents when you’re away from your laptop without having predefined projects and making sure to have the right apps open. Quick ideas, vLLM-studio was done entirely in Openclaw to start https://t.co/oKOfYCprPu

@shangobashi @NousResearch hmmm.... I see this on latest.. I have a feeling the debug logs wont catch this but, can you run /debug and send me the links it generates? https://t.co/AlT43Hl8Nu

Spent 4 months and built Omi for Desktop, your life architect It sees your screen, hears your conversations and tells you what to do next It’s like having a second brain that actually pays attention Open source, local, link below https://t.co/DwcjwKkQk9

What if virtual humans could see, think, and act in 3D worlds like us?! We present Visually-Grounded Humanoid Agents 🎉 Our agents 👀perceive via RGB-D vision, 🧠plan with context-aware reasoning, and 🏃act with full-body motion in 3D scenes. Check 🔗 https://t.co/kd0zCu7W2h https://t.co/VQZnjE2Pnx

@LobsterKill https://t.co/f18drIO2Ge

推荐个插件叫 YouTube to NotebookLM，能一键把油管频道所有视频打造成一个知识库。当然也可以单独添加单个视频和合集，太好用了！ https://t.co/yQamUXWwt6

+2 more

推荐个插件叫 YouTube to NotebookLM，能一键把油管频道所有视频打造成一个知识库。当然也可以单独添加单个视频和合集，太好用了！ https://t.co/yQamUXWwt6

+2 more

Hermes dashboard 支持中文了 👍 https://t.co/nWx877JASS

Hermes dashboard 支持中文了 👍 https://t.co/nWx877JASS

Windows的WSL子系统迁移成功， 迁移后Hermes Agent不受任何影响，正常运行， 帮我的C盘一下子腾了15G空间， 感谢大佬@kylegeeks提供的方法。 迁移方法很简单： 1/ 获取WSL子操作系统名称NAME wsl -l -v 2/ 关闭WSL子系统 其实这步只要你把所有运行的终端窗口关了它也就停了，不过为了保险，还是执行一下。 wsl --shutdown 3/ 将WSL子系统导出到D盘，记得先建一个文件夹单独存放，这里的Ubuntu就是第一步的NAME，如果跟我的不同，你就用第一步显示的NAME即可。 wsl --export Ubuntu D:\WSL\wsl-export.tar 4/ 注销原来的WSL操作系统 wsl --unregister Ubuntu 5/ 导入到目标位置 wsl --import Ubuntu D:\WSL D:\WSL\wsl-export.tar 6/ 启动WSL wsl 7/ 启动Hermes网关 hermes gateway 正常的话是一路顺利执行，异常的话还没遇到，有遇到异常的欢迎留言。