What the smart people are recommending. 7861 books, tools, and products endorsed by the thinkers absorb.md tracks. Ranked by how many times each has been recommended across compiled podcasts, papers, posts, and tweets.
βThe idea of this repo is that instead of asking a question to your favorite LLM provider (e.g. OpenAI GPT 5.1, Google Gemini 3.0 Pro, Anthropic Claude Sonnet 4.5, xAI Grok 4, eg.c), you can group themβ¦β
βA demo of using RSC and Vercel Postgres, legally brought to lifeβ
βWe open-source the training code and model checkpoints at https://github.com/facebookresearch/spidr-adapt.β
βRun FLUX.2 on Replicateβ
βWe open-source FailFast at https://github.com/ruipeterpan/failfast.β
βUh your biggest GitHub project is probably SEC lists which you did for Kali Linux with 70,000 uh GitHub.β
βThis repository contains code to run evals released by Mistral AI as well as standardized prompts, parsing and metrics computation for popular academic benchmarks.β
βYou can also install [eslint-plugin-react-x](https://github.com/Rel1cx/eslint-react/tree/main/packages/plugins/eslint-plugin-react-x) and [eslint-plugin-react-dom](https://github.com/Rel1cx/eslint-reaβ¦β
βYou can also install [eslint-plugin-react-x](https://github.com/Rel1cx/eslint-react/tree/main/packages/plugins/eslint-plugin-react-x) and [eslint-plugin-react-dom](https://github.com/Rel1cx/eslint-reaβ¦β
β# emoji-todo β A simple app to demonstate the ease of fetching and mutating data with Next.js App Router, RSC, and Server Actions. # emojis-todoβ
βTo scale SPF, we curate ClimateSuite, the largest collection of Earth system simulations to date, comprising over 33,000 simulation-years across ten climate models and the first dataset to include simβ¦β
βCode is available at https://github.com/facebookresearch/eb_jepa.β
β- [maturin](https://github.com/PyO3/maturin) - The Rust equivalent that inspired this toolβ
β# Resend Robot **letter_opener for the [Resend](https://resend.com) gem.**β
βif people want to just like play around with Deep Funding ideas if you go to github.com/defunding/scoring I have a couple of fun demos there that are going to show what Deep Funding might look like inβ¦β
β- [pip-binary-factory](https://github.com/Bing-su/pip-binary-factory) - Template for packaging pre-built binariesβ
βPipes through [nix-output-monitor](https://github.com/maralorn/nix-output-monitor) when available.β
βUses z-libs for safe string/vector handlingβ
βTo mitigate these issues, we introduce stable-worldmodel (SWM), a modular, tested, and documented world-model research ecosystem that provides efficient data-collection tools, standardized environmentβ¦β
βWe conclude with reflections on human-AI collaboration in mathematics and share all prompts as well as model outputs at https://github.com/google-deepmind/superhuman/tree/main/aletheia.β
βOur code is available at https://github.com/galilai-group/cjepa.β
βI recovered that zip file from the Internet Archive and used it to populate this GitHub repository. The repository is served via GitHub Pages here: https://simonw.github.io/cia-world-factbook-2020/β
βCode is available at https://github.com/galilai-group/llm-jepa#stp.β
βwe had a big impact on the AI research community um with things like PyTorch and you Fair seek and you know uh all the image recognition and uh open source systems that we put outβ
βFeice which is kind of a similarity search system and I mean there's there's like a thousand open source projects that fair produced which you know all of which have had a very very big impact on the β¦β
βEinsteinArena is open-source and the leaderboard is live. We welcome contributions and feedback!β
βI i I sent a link to Alex earlier uh to an open the my starter kit that I built out of put on GitHub.β
βOpen-source: complete codebase covering multiple simulation backends, training, retargeting, and real-world inference. Infra built for humanoid, but also readily modified for quadruped (also included)β¦β
β# amux β GitHub repo # amux β agentic mux Named tmux panels for AI agents and humans. Run commands in persistent background panels, tail their output with byte-offset continuation, andβ
β# liquid-il β A Liquid template engine, 100% vibe coded by Claude Code against liquid-specβ
β# liquid-il β A Liquid template engine, 100% vibe coded by Claude Code against liquid-specβ
βEarlier this year we open sourced a model called root n1 that operationalizes this this approach. So the group n1 model it's got system one and system two right system two is a v that does reasoning.β
βmicrosoft who owns mojang studio who made minecraft they open source a framework called malmo that essentially gives a programmatic api um for ai to control minecraft and our work is built upon malmoβ
βmy ro is an abstraction layer on top of malmo that provides a nicer python api and also like just in general a better interface and my dojo is built upon my roβ
βCode is available at https://github.com/helenqu/physical-representation-learning.β
βA Go CLI tool that drives a persistent headless Chrome instance using the [rod](https://github.com/go-rod/rod) browser automation library.β
βI have this like running obsession of like maybe a decade or two of just like simplifying and boiling down the uh basically LLMs uh to like their bare essence. And I've had a number of projects along β¦β
βI have this like running obsession of like maybe a decade or two of just like simplifying and boiling down the uh basically LLMs uh to like their bare essence. And I've had a number of projects along β¦β
βCheck out [elixir/README.md](elixir/README.md) for instructions on how to set up your environment and run the Elixir-based Symphony implementation.β
β# client-ts β TS Client library for Mistral AI platformβ
βhttps://github.com/openai/chatkit-jsβ
β- [Starter app](https://github.com/openai/openai-chatkit-starter-app) - Clone a repo to start with a fully working templateβ
β- [Samples](https://github.com/openai/openai-chatkit-advanced-samples) - See working examples of ChatKit and get inspiredβ
βWe recommend using this library when working with models that use the [harmony response format][harmony-format]β
βI have a a couple of GitHub repositories that I specifically use for this. I've got one called tools, simonw/tools and that's little HTML and JavaScript um tools that I've built or that I've got Claudβ¦β
βHiring engineers with 5 years of experience in @ππππππππ/ππππππ‘π to create the web rendering toolkit of the futureβ
βChallenges like the [NanoGPT Speedrun](https://github.com/KellerJordan/modded-nanogpt), which optimizes for a form of L(T) (~lowest time given constrained loss) or the [NanoGPT Slowrun](https://qlabs-β¦β
βThen the other one I have is Simon W/ressearch on GitHub which are AIdriven research projects.β
βWe release all code and experiments at https://github.com/KE-UniLiv/IDEA2β
βCode: https://github.com/capgym/cap-xβ
βNice clean github: https://github.com/lucas-maes/le-wmβ
βI think two things. One is that what we currently experience is like a super super tiny thing of what is about to happen you know just because like >> right it's a glimpse. It's a glimpse like you knoβ¦β
βRun [Codex](https://github.com/openai/codex#codex-exec) from a GitHub Actions workflow while keeping tight control over the privileges available to Codex. This action handles installing the Codex CLI β¦β
βCarl open-sourced his personal operating system at github.com/carlvellotti/carls-product-osβ
βThink of fan wikis like Tolkien Gateway β thousands of interlinked pages covering characters, places, events, languages, built by a community of volunteers over years. You could build something like tβ¦β
βQMD combines BM25 full-text search, vector semantic search, and LLM re-rankingβall running locally via node-llama-cpp with GGUF models.β
βPlease head on to our [contribution guideline](https://docs.mistral.ai/guides/contribute/).β
βmesh-llm: pool compute to run open models. built by @michaelneale at block: https://docs.anarchai.orgβ
βIf you have cool examples showcasing Mistral models, feel free to share them by submitting a PR to this repo.β
βembeddinggemma-300M-Q8_0 | Vector embeddings (default)β
βqwen3-reranker-0.6b-q8_0 | Re-rankingβ
βgit clone https://github.com/tobi/qmdβ
β# client-python β Python client library for Mistral AI platformβ
βFinally, we're the company behind the AGI protocol, which is one of the fastest growing TypeScript AI projects.β
βnow uh and there's sort of a threshold right if the AI can help you make a chemical weapon but only as much as a Google search could have already helped you then that's not so concerning right but if β¦β
βThis repository catalogs skills for use and distribution with Codex.β
βThere are similar experiments going on out of um a lab at Stanford um you can find it at hazy research on GitHub and they've been doing lots of work as well to try to use ssms for language modelingβ
βHe currently is writing this thing that he talked about earlier the software package called stem which is useful for talking about air correction and by using this package he sort of has built the pacβ¦β
βThere's tons of open source going on if you're interested you should just look around circ uh you know but other other platforms kids kit uh you know there's the unitary fund which does open source soβ¦β
βGitHub's official status page does look a bit better, to be fair, but still not great.β
βGitHub stopped updating its status page with aggregate uptime numbers some time ago. If you use it regularly, you might have a feeling why. This is the missing version. We rebuild platform-wide and peβ¦β
βA Hollywood actress and her crypto friend used Plaid to VIP code a memory um agentic thing. What the [Β __Β ] They have a GitHub and everything. It's like literally github.com/miladovich.β
βanybody that want to build graph we have a good uh so-called LLM graph rack stack on GitHub that is sponsored by new forj and out of the box just spin up your dockerβ
βCode is available at https://github.com/DISCO-design/DISCO.β
βthere's a GitHub repo here that you can go to and and you can start to contribute or use use the use the data um there's documentation available as well and there's sample applicationsβ
βHave you heard of Mark Robber? Does this name any of you who created like the ultimate squirrel ninja warrior course in his backyard? Put on YouTube. Let me let me Yeah, there we go. All right. Mark Rβ¦β
βI just started this repo called awesome Claude Skills and moment.β
βAnd there's a one package I thought is pretty useful recently called supercloud. It's a open source package that comes with bunch of commands that they predefine and build. For example, I can do slashβ¦β
βOne of them is called CC undo. So this is a package that will automatically detect all the changes that cloud code has made to your file and allow it to roll back.β
βWill and Johannes work at Prime Intellect which is one of the coolest neols in AI right now.β
βAnd this is an open source toolkit, so go check it out.β
βYou just need to install the package by doing mpm install-g superdesign/ci at the latest and then call superdesign login which will pop up this screen to allow you to authorize and in the end you can β¦β
βWe believe that the TEC platform and dataset provide a valuable foundation for understanding human trial-and-error behavior and for developing more capable AI systems. Platform and dataset are publiclβ¦β
βWe will release model checkpoints, training data, code, and a unified evaluation harness to enable reproducibility and accelerate open research on web agents.β
βWe will release model checkpoints, training data, code, and a unified evaluation harness to enable reproducibility and accelerate open research on web agents.β
βTo enable its use in specialized materials discovery problems and support interdisciplinary research, we open-source our code and provide additional project information at https://github.com/znowu/Cliβ¦β
βCode has been made available at https://github.com/yuzhi535/FDSM.β
βThe complete parts list, assembly guidelines, and processing code for the SCANS gripper are accessible at: https://parses-lab.github.io/scans/.β
βSo, that was built on top of OpenI's open- source codeex.β
βSo Quen, the open- source model out of Alibaba has passed, I think, 400 million downloads. Of course, that's released like these other models under the Apache 2.0 open source license. So, very open asβ¦β
βSo, the the superpowers um repo or agency agents, right? This I'm sure many of you guys have seen this repo. It has 60,000 stars where there's some over aundred agents um and you can import them all iβ¦β
βSo, the the superpowers um repo or agency agents, right? This I'm sure many of you guys have seen this repo. It has 60,000 stars where there's some over aundred agents um and you can import them all iβ¦β
βThere's a uh a game studio. Yeah, the Don Cheetos game studio where you know there's a creative director, producer, technical director, there's all sorts of skills around creating assets.β
βProject page and source code: https://github.com/Blanketzzz/Geo2Soundβ
βyou can go on github.com/OpenAI slash codex and you have like a... you can sort of build on top of that.β
βAnd with Dino V3, we release a specialized backbone for satellite imagery tasks. This open-source release includes our training code and model weights, efficient models, and alternative architectures,β¦β
βAndre Carpathy opensourced what he called auto research... He put all of his code up on GitHub... give an AI agent a small but real large language model training setup and let it experiment autonomousβ¦β
βThe Ethereum Foundation this week actually released a post-quantum roadmap website. It's called pq.etherium.org. And it really specifies the plan and the milestones.β
βI did see a very cool website called PQ Ethereum.org or whatever.β
βIf you have a DAP that can profit from this, be in touch with us. The website is ez.io. If you're an L2, same. If you're a user and you want to feedback on this or you just want to look at our GitHub,β¦β