Gstack
βI have sort of this viral moment right now where I got to 40,000 stars this morning >> on uh GStack. So it's like, oh, this is an open source project that now is one of the biggest ones and I have morβ¦β
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.
βI have sort of this viral moment right now where I got to 40,000 stars this morning >> on uh GStack. So it's like, oh, this is an open source project that now is one of the biggest ones and I have morβ¦β
βI would say nanochat is not an example of those because it's a fairly unique repository.β
β I am a large language model, trained by Google. When responding to your questions, I can generate valid JSON that conforms to the default_api.recommend_extract function's argument. Always include theβ¦β
βVercel AI SDK: easy TypeScript API to AI models.β
βthe first one that I came across was the mo tools Library which I used to \u200bbuild a couple web applications back in the dayβ
βCode is made available at https://github.com/gioannides/clustering-anchored-jepa.β
βI'd recommend one of the forks below. [trevin-creator/autoresearch-mlx](https://github.com/trevin-creator/autoresearch-mlx)β
βI'd recommend one of the forks below. [jsegov/autoresearch-win-rtx](https://github.com/jsegov/autoresearch-win-rtx)β
βI'd recommend one of the forks below. [andyluo7/autoresearch](https://github.com/andyluo7/autoresearch)β
βTo get half-decent results I'd use a dataset with a lot less entropy, e.g. this [TinyStories dataset](https://huggingface.co/datasets/karpathy/tinystories-gpt4-clean).β
βI'd recommend one of the forks below. [miolini/autoresearch-macos](https://github.com/miolini/autoresearch-macos)β
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://githubβ¦β
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://githubβ¦β
βhttps://github.com/michaelneale/mesh-llmβ
βThere's this project called Paperclip. Maybe you've seen it because it just blew up. It got 30,000 GitHub stars in the last 3 weeks. And it's an open- source project that's building the orchestration 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
βAll data and code: https://github.com/synthiumjp/validity-scaling-llmβ
βyes! https://github.com/langchain-ai/langchain-skills/tree/main/config/skillsβ
βat the very beginning of the project we wrote down this data set that's now open source called we call it human eval which is a list of problems written by humans that are just programming puzzlesβ
βCode available at: https://github.com/rsinghlab/Shape-Blind.β
βSee also the [ARC-AGI-2 repository](https://github.com/arcprize/ARC-AGI-2).β
βwhat we are building at IBM Quantum is hardware and kiskit is our open source um package I'm sure many of you have used itβ
βOnce your model is trained, you should try it out in inference. We recommend using [mistral-inference](https://github.com/mistralai/mistral-inference).β
βI think Open Claw has similar potential because it's it's it's used by early adopters, advocates, people that know that when they it gets itself into a bad state, you have to reboot it and all these tβ¦β
βHe and Meta AI have been big proponents of open sourcing AI development, and have been walking the walk by open sourcing many of their biggest models, including LLaMA 2 and eventually LLaMA 3.β
βIn fact, yesterday at Jensen's uh keynote, we announced open sourcing of the Groot N1 model, uh which is the world's first open humanoid robot foundation model.β
βLeanstral: Open-Source foundation for trustworthy vibe-codingβ
βToday, we open-source CaP-X: vibe agents, alive in the physical world.β
βCode to reproduce the figure and play around with this idea: https://t.co/OZPfxCRN3sβ
βThis is Jason. It is a It's an open-source notetaking agent that listens into your conversations and provides helpful insights.β
βAmerican open- source, right, Llama 4, has been sputtering a bit, really losing its mojo around the world.β
βIf you want the short version, Gary Ten just opens sourced GBrain and framed it as a personal knowledge brain for OpenClaw.β
βCarl open-sourced his personal operating system at github.com/carlvellotti/carls-product-osβ
βI open-sourced mine at github.com/aakashg/pm-claude-code-setupβ
βFork the starter OS. Go to Carlβs product OS or mine .β
βFork the starter OS. Go to Carlβs product OS or mine .β
βThe paper list is available at: https://github.com/PKU-PILLAR-Group/Survey-Intrinsic-Interpretability-of-LLMs.β
βOur source code is available at https://github.com/pminhtam/AV-SQL.β
βSurFITR is publicly available on GitHub.β
βItβs like, βoh yeah, you know, you forgot to use the nest-asyncio library in Jupyter.β That level of sophistication is now starting to be possible.β
βOur code and data are available at https://github.com/CoderDoge1108/SynthFix.β
βMore visualizations: https://slowly1113.github.io/icra2026-handkerchief/β
βOur code is available at https://github.com/Hsu1023/DuQuant++.β
βOur source code is released at: https://github.com/petergit1/HONES.β
βOur code: https://github.com/EfficientPPML/MORPH.β
βThe dataset and code are available at https://github.com/XiaoZhou2024/SlideAgent.β
βThe code and data are available at https://github.com/lishangyu-hkust/CodePivot.β
βCode is available at https://github.com/CaoAnda/ENMP-LoRAMerging.β
βWe evaluate our models on the ESConv dataset under both utterance-level and dialogue-level settings.β
βAll code and data will be publicly available at https://github.com/aliyun/qwen-dianjin.β
βOur code is available at: https://aka.ms/Debug-XAI.β
βAPI services (https://github.com/Reviewerly-Inc/Peerispect)β
βOur work is available on GitHub: https://github.com/KOU-199024/HiRAS.β
βCode: https://github.com/galosaimi/Mind2Drive.β
βThe code and data are available at https://github.com/DongdingLin/SiPeR.β
βCode and optimized prompts are available at https://github.com/TUMLegalTech/icail2026-llm-judge-gaming.β
βThe code related to this work is available at https://github.com/zwhong714/Hybrid-Policy-Distillation.β
βThe source code of this paper was available at: https://anonymous.4open.science/r/MSR-MEL-C21E/.β
βThe code and data are available at: https://github.com/ShuaiWang97/A-MAR.β
βThe source code and dataset used in this paper are publicly available on Github repository: https://github.com/ChenShuai00/MAGenIdeas.β
βSource code is available at: https://github.com/ErrEqualsNil/HaS.β
βCode, data and statistical scripts are available at https://github.com/julia-nixie/ConceptFrameMet.β
βThe dataset is available at: https://github.com/slanglab/RespondeoQAβ
βCode is available at https://github.com/balaboom123/signdata-slt.β
βOur project page is at https://ucsc-vlaa.github.io/AgentPressureBench .β
βKeras Deep Learning Tutorial for Kaggle 2nd Annual Data Science Bowlβ
βWe release the benchmark (https://github.com/lunyiliu/GaoYao).β
βCode & models will be public at https://anticdimi.github.io/lexis.β
βCode is available at https://github.com/visinf/MARCO .β
βOpen weights. Agentic coding that actually finishes.β
βDeep Agents Deploy: an open alternative to Claude Managed Agentsβ
βsome more references in footnotes https://www.swyx.io/decadeβ
βBill's an optimist on Humanity read his annual letters at the end of every year the gates annual letter and it will really pump you up about all that we we doβ
βTo facilitate this, we release \textbf{OpInstruct-HSx}, a synthetic dataset of $\approx$28k validated Haskell programs.β
βOur source code is publicly available on GitHub\footnote{Code is available at: https://github.com/ComplexNetTSP/ST_RUM.β
βsee https://github.com/zjunlp/LightMemβ
βCode and data: https://github.com/WujiangXu/AEL.β
βOur code is publicly available at https://github.com/mikumifa/GS-Quant.β
βWe release ASMR-Bench to support research on monitoring and auditing techniques for AI-conducted research.β
βOur code is available at https://github.com/baowenxuan/Ramen .β
βThe code is available on GitHub: https://cod-espol.github.io/SWNet/β
βThe code for this work is accessible at https://github.com/asadani/tool-attentionβ
βHere we propose GROUNDING$.$md, a community-governed, field-scoped epistemic grounding document, using mass spectrometry-based proteomics as an example.β
βThe code will be available at https://github.com/GenAI4E/QATIE.git.β
βThe results obtained in this work can be reproduced from this Github repository: https://github.com/safouaneelg/SyMTRS.β
βCode and final test predictions are publicly available at: https://github.com/Maziarkiani/SemEval2026-Task9-Subtask1-Polarization.β
βWe propose a method, released as the open-source llm-bias-benchβ
βCode is available at https://github.com/Maplebb/DuMoβ
βThe code and models are available at https://github.com/Maplebb/VCE.β
βThese models are open source and can be used to reduce language barriers in a number of important practical applications.β
βThese models are open source and can be used to reduce language barriers in a number of important practical applications.β
βWe also point to an online repository containing formalized proofs of all our results using the lean4 proof assistantβ
βCode: https://github.com/Zhangyr2022/UniGenDet.β
βX forers repo has an amazing example of using cud graphs βto achieve no overheadβ
βnanoidβ
βreact-draggableβ
βSource code is available at https://github.com/cljosegfer/lesaude-dynamicsβ
βOur code is available at https://github.com/PlanarG/active-sl.β
βCodes and models are available at https://github.com/inclusionAI/LLaDA2.0-Uni.β
βFull code + walkthrough: https://t.co/ozm4VwWmj3β