absorb.md

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.

AllπŸ“š BooksπŸ›  ToolsπŸ“± AppsπŸ’Š SupplementsπŸŽ“ Courses🎬 MoviesπŸ“Ί ShowsπŸ“¦ ProductsπŸ”§ ServicesπŸ“„ PapersπŸ‘€ People🎟 EventsπŸ’» Repos✨ Skills
Timeframe:All timeLast 7 daysLast 30 daysLast 90 days
πŸ’» ReposΓ—10 mentions

Gstack

by Garry Tan

β€œI 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 mor…”

youtube: Orchestrating Autonomous AI Workforces β€” by Garry Tan β€” 2026-04-12
Endorsed by Garry Tan, FranΓ§ois Chollet, Greg Isenberg
Details β†’Visit β†—
πŸ’» ReposΓ—7 mentions

Nanochat

β€œI would say nanochat is not an example of those because it's a fairly unique repository.”

github_readme: llm-mrchatterbox: Running a Victorian-era LLM Locally with LLM β€” by Simon Willison β€” 2026-03-30
Endorsed by Simon Willison, Andrej Karpathy, Andrej Karpathy
Details β†’Visit β†—
πŸ’» ReposΓ—5 mentions

Nanogpt

by Andreij Karpathy

β€œ 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 the…”

youtube: The Future of Engineering in the Age of AI Agents β€” by Andrej Karpathy β€” 2026-03-20
Endorsed by Andrej Karpathy, Andrej Karpathy, Andrej Karpathy
Details β†’Visit β†—
πŸ’» ReposΓ—4 mentions

Vercel Ai Sdk

β€œVercel AI SDK: easy TypeScript API to AI models.”

youtube: How to Build Vertical AI Agents with Vercel AI SDK β€” by AI Jason β€” 2026-04-10
Endorsed by AI Jason, Guillermo Rauch
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Mootools

by Guillermo Rauch

β€œthe first one that I came across was the mo tools Library which I used to \u200bbuild a couple web applications back in the day”

youtube: Vercel's Strategy for Scaling Developer Experience in the AI Era β€” by Guillermo Rauch β€” 2025-12-10
Endorsed by Guillermo Rauch
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Gioannidesclusteringanchoredjepa

by gioannides

β€œCode is made available at https://github.com/gioannides/clustering-anchored-jepa.”

paper: GMM-Anchored JEPA Improves Self-Supervised Speech Representation β€” by Yann LeCun β€” 2026-01-30
Endorsed by Yann LeCun
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Trevincreatorautoresearchmlx

β€œI'd recommend one of the forks below. [trevin-creator/autoresearch-mlx](https://github.com/trevin-creator/autoresearch-mlx)”

github_readme: Autonomous AI Agents for LLM Research and Optimization β€” by Andrej Karpathy β€” 2026-03-26
Endorsed by Andrej Karpathy
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Jsegovautoresearchwinrtx

β€œI'd recommend one of the forks below. [jsegov/autoresearch-win-rtx](https://github.com/jsegov/autoresearch-win-rtx)”

github_readme: Autonomous AI Agents for LLM Research and Optimization β€” by Andrej Karpathy β€” 2026-03-26
Endorsed by Andrej Karpathy
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Andyluo7autoresearch

β€œI'd recommend one of the forks below. [andyluo7/autoresearch](https://github.com/andyluo7/autoresearch)”

github_readme: Autonomous AI Agents for LLM Research and Optimization β€” by Andrej Karpathy β€” 2026-03-26
Endorsed by Andrej Karpathy
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Tinystories Dataset

by karpathy

β€œTo 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).”

github_readme: Autonomous AI Agents for LLM Research and Optimization β€” by Andrej Karpathy β€” 2026-03-26
Endorsed by Andrej Karpathy
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Mioliniautoresearchmacos

β€œI'd recommend one of the forks below. [miolini/autoresearch-macos](https://github.com/miolini/autoresearch-macos)”

github_readme: Autonomous AI Agents for LLM Research and Optimization β€” by Andrej Karpathy β€” 2026-03-26
Endorsed by Andrej Karpathy
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Nanogpt Slowrun

β€œChallenges 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://github…”

github_readme: OpenAI’s Parameter Golf Challenge Pushes LLM Efficiency and Innovation β€” by OpenAI β€” 2026-03-30
Endorsed by OpenAI
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Nanogpt Speedrunning

β€œChallenges 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://github…”

github_readme: OpenAI’s Parameter Golf Challenge Pushes LLM Efficiency and Innovation β€” by OpenAI β€” 2026-03-30
Endorsed by OpenAI
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Michaelnealemeshllm

β€œhttps://github.com/michaelneale/mesh-llm”

tweet: Jack Dorsey Endorses Mesh-LLM Project on Decentralized AI β€” by Jack Dorsey β€” 2026-04-02
Endorsed by Jack Dorsey
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Paperclip

β€œThere'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 …”

youtube: Orchestrating Autonomous AI Workforces β€” by Garry Tan β€” 2026-04-12
Endorsed by Garry Tan, Greg Isenberg, Greg Isenberg
Details β†’Visit β†—
πŸ’» ReposΓ—3 mentions

Micro Gpt

by karpathy

β€œI 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 …”

paper: Efficient Data Deletion Scheme for Deep Learning Models β€” 2026-04-09
Endorsed by Andrej Karpathy, Andrej Karpathy
Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Synthiumjpvalidityscalingllm

β€œAll data and code: https://github.com/synthiumjp/validity-scaling-llm”

paper: LLM Metacognitive Self-Reports Need Validity Screening Before Interpretation β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Langchainskills

β€œyes! https://github.com/langchain-ai/langchain-skills/tree/main/config/skills”

tweet: LangChain Offers Skills Configuration Analogous to Anthropic's Claude-API Skill β€” by Harrison Chase β€” 2026-04-25
Endorsed by Harrison Chase, Harrison Chase
Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Human Eval

β€œat 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 puzzles”

Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Rsinghlabshapeblind

β€œCode available at: https://github.com/rsinghlab/Shape-Blind.”

Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Arcagi2 Repository

by ARC Prize

β€œSee also the [ARC-AGI-2 repository](https://github.com/arcprize/ARC-AGI-2).”

Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Kiskit

by IBM

β€œwhat we are building at IBM Quantum is hardware and kiskit is our open source um package I'm sure many of you have used it”

Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Mistralinference

β€œOnce your model is trained, you should try it out in inference. We recommend using [mistral-inference](https://github.com/mistralai/mistral-inference).”

github_readme: Mistral Inference: Open-weight Model Deployment and Usage β€” by Mistral AI β€” 2026-02-26
Endorsed by Mistral AI, Mistral AI
Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Openclaw

by Pete

β€œI 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 t…”

youtube: AI Faces Public Backlash Amid Polling Slump, But Nvidia Counters with Jobs Narrative; Meta's Flagship Model Falters β€” by Alex Kantrowitz β€” 2026-04-13
Endorsed by Alex Kantrowitz, Guillermo Rauch
Details β†’
πŸ’» ReposΓ—2 mentions

Llama 2

β€œHe 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.”

youtube: Emerging AI Inference Accelerators: A Landscape of Specialization β€” by FranΓ§ois Chollet β€” 2026-04-10
Endorsed by FranΓ§ois Chollet
Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Groot N1 Model

by NVIDIA Gear Lab and Project Groot

β€œIn 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.”

youtube: The Future of Humanoid Robotics: Progress, Challenges, and Societal Impact β€” by Jim Fan β€” 2026-04-07
Endorsed by Jim Fan, Jim Fan
Details β†’
πŸ’» ReposΓ—2 mentions

Leanstral

by Mistral AI

β€œLeanstral: Open-Source foundation for trustworthy vibe-coding”

blog: Leanstral: An Open-Source, Efficient Prover for Formal Verification β€” by Mistral AI β€” 2026-03-16
Endorsed by Mistral AI
Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Capx

β€œToday, we open-source CaP-X: vibe agents, alive in the physical world.”

tweet: NVIDIA, Berkeley, Stanford, and CMU collaborate to open-source CaP-X under MIT license β€” by Jim Fan β€” 2026-04-01
Endorsed by Jim Fan, Jim Fan
Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Code To Reproduce The Figure And Play Around With This Idea

β€œCode to reproduce the figure and play around with this idea: https://t.co/OZPfxCRN3s”

tweet: Spurious Correlations in Time Series Visualization β€” by FranΓ§ois Chollet β€” 2026-04-05
Endorsed by FranΓ§ois Chollet
Details β†’
πŸ’» ReposΓ—2 mentions

Open Oats

by Yasin Ali Raheem

β€œThis is Jason. It is a It's an open-source notetaking agent that listens into your conversations and provides helpful insights.”

youtube: Navigating the AI Agent Economy: From Subsidies to Self-Sufficiency β€” by Jason Calacanis β€” 2026-04-07
Endorsed by Jason Calacanis, Jason Calacanis
Details β†’
πŸ’» ReposΓ—2 mentions

Llama 4

by Meta

β€œAmerican open- source, right, Llama 4, has been sputtering a bit, really losing its mojo around the world.”

youtube: US Economic Rebalancing and the Ascendance of Chinese AI β€” by Bg2 Pod β€” 2026-04-10
Endorsed by Bg2 Pod, Yann LeCun
Details β†’Visit β†—
πŸ’» ReposΓ—2 mentions

Gbrain

β€œIf you want the short version, Gary Ten just opens sourced GBrain and framed it as a personal knowledge brain for OpenClaw.”

tweet: Garry Tan Builds AI Coding Tool in 9 Days Using His Own Hourly X Feed β€” by Garry Tan β€” 2026-04-13
Endorsed by Garry Tan, Garry Tan
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Carls Personal Operating System

by Carl Vellotti

β€œCarl open-sourced his personal operating system at github.com/carlvellotti/carls-product-os”

Recommended on The Growth Podcast β€” 2026-04-08
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Aakashs Pmclaudecodesetup

by Aakash Gupta

β€œI open-sourced mine at github.com/aakashg/pm-claude-code-setup”

Recommended on The Growth Podcast β€” 2026-04-08
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Carls Product Os

by Carl Vellotti

β€œFork the starter OS. Go to Carl’s product OS or mine .”

Recommended on The Growth Podcast β€” 2026-04-08
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

My Pm Os

by Aakash Gupta

β€œFork the starter OS. Go to Carl’s product OS or mine .”

Recommended on The Growth Podcast β€” 2026-04-08
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Surveyintrinsicinterpretabilityofllms

β€œThe paper list is available at: https://github.com/PKU-PILLAR-Group/Survey-Intrinsic-Interpretability-of-LLMs.”

paper: Survey Classifies Intrinsic LLM Interpretability into Five Core Design Paradigms β€” 2026-04-20
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Avsql

β€œOur source code is available at https://github.com/pminhtam/AV-SQL.”

paper: AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views β€” 2026-04-09
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Surveillance Forgery Image Test Range Surfitr

β€œSurFITR is publicly available on GitHub.”

paper: SurFITR Dataset: Advancing Surveillance Image Forgery Detection β€” 2026-04-09
Details β†’
πŸ’» ReposΓ—1 mentions

Nestasyncio Library

β€œIt’s like, β€œoh yeah, you know, you forgot to use the nest-asyncio library in Jupyter.” That level of sophistication is now starting to be possible.”

Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Synthfix

β€œOur code and data are available at https://github.com/CoderDoge1108/SynthFix.”

paper: SynthFix Boosts LLM Code Vulnerability Repair via Adaptive Neural-Symbolic Training β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Icra2026handkerchief

β€œMore visualizations: https://slowly1113.github.io/icra2026-handkerchief/”

paper: Dexterous Tendon-Driven Wrist Achieves 99% Handkerchief Unfolding via Hierarchical Control and Particle-Spring Modeling β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Duquant

β€œOur code is available at https://github.com/Hsu1023/DuQuant++.”

paper: DuQuant++ Simplifies Outlier-Aware Rotation for MXFP4, Halving Costs and Boosting LLM Accuracy β€” 2026-04-21
Details β†’
πŸ’» ReposΓ—1 mentions

Hones

β€œOur source code is released at: https://github.com/petergit1/HONES.”

paper: HONES Enables Task-Aware Causal Attribution and Steering of FFN Neurons in Multi-Task VLMs via Attention Heads β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Morph

β€œOur code: https://github.com/EfficientPPML/MORPH.”

paper: MORPH Repurposes AI ASICs for High-Throughput ZKP Proving via Kernel Reformulation β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Slideagent

β€œThe dataset and code are available at https://github.com/XiaoZhou2024/SlideAgent.”

paper: DynaSlide: Benchmark and SlideAgent Enable NL-Driven Dynamic Updates to User-Templated Presentation Slides β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Codepivot

β€œThe code and data are available at https://github.com/lishangyu-hkust/CodePivot.”

paper: CodePivot Enables Multilingual Code Transpilation via Python Pivot and RL Without Parallel Data β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Enmploramerging

β€œCode is available at https://github.com/CaoAnda/ENMP-LoRAMerging.”

paper: Evolutionary Pruning of Negative LoRA Modules Enhances Merging Performance β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Esconv Dataset

β€œWe evaluate our models on the ESConv dataset under both utterance-level and dialogue-level settings.”

paper: Multi-Strategy Utterances Boost Emotional Support Conversation Effectiveness β€” 2026-04-21
Details β†’
πŸ’» ReposΓ—1 mentions

Qwendianjin

by Alibaba (Aliyun)

β€œAll code and data will be publicly available at https://github.com/aliyun/qwen-dianjin.”

paper: Multi-Strategy Utterances Boost Emotional Support Conversation Effectiveness β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Debugxai

β€œOur code is available at: https://aka.ms/Debug-XAI.”

paper: Contrastive LRP Attribution Reveals LLM Failure Patterns on Real Benchmarks with Key Limitations β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Reviewerlyincpeerispect

by Reviewerly Inc.

β€œAPI services (https://github.com/Reviewerly-Inc/Peerispect)”

paper: Peerispect: Automating Claim Verification in Peer Reviews via NLP Pipelines β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Kou199024hiras

β€œOur work is available on GitHub: https://github.com/KOU-199024/HiRAS.”

paper: HiRAS: Hierarchical Multi-Agent Coordination Breaks the Sequential Pipeline Bottleneck in Paper-to-Code Reproduction β€” 2026-04-21
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Galosaimimind2drive

β€œCode: https://github.com/galosaimi/Mind2Drive.”

paper: EEG Can Predict Driving Manoeuvres Up to 1 Second in Advance with 90%+ Accuracy in Real-World Conditions β€” 2026-04-22
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Siper

β€œThe code and data are available at https://github.com/DongdingLin/SiPeR.”

paper: SiPeR Framework Enhances Situated Conversational Recommendation via Scene Transition Estimation and Bayesian Preference Inference β€” 2026-04-23
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Icail2026llmjudgegaming

β€œCode and optimized prompts are available at https://github.com/TUMLegalTech/icail2026-llm-judge-gaming.”

paper: Automatic Prompt Optimization Outperforms Human Design in LLM-as-a-Judge for Legal QA, with Lenient Judges Enabling Better Transfer β€” 2026-04-23
Details β†’
πŸ’» ReposΓ—1 mentions

Hybridpolicydistillation

β€œThe code related to this work is available at https://github.com/zwhong714/Hybrid-Policy-Distillation.”

paper: Hybrid Policy Distillation Unifies and Enhances LLM Knowledge Distillation β€” 2026-04-23
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Msrmel

β€œThe source code of this paper was available at: https://anonymous.4open.science/r/MSR-MEL-C21E/.”

paper: LLM-Driven Multi-Perspective Evidence Synthesis Outperforms Prior Unsupervised Multimodal Entity Linking β€” 2026-04-23
Details β†’
πŸ’» ReposΓ—1 mentions

Shuaiwang97amar

by Shuai Wang

β€œThe code and data are available at: https://github.com/ShuaiWang97/A-MAR.”

paper: Reasoning-Conditioned Retrieval Outperforms Static MLLMs for Fine-Grained Artwork Understanding β€” 2026-04-22
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Magenideas

β€œThe source code and dataset used in this paper are publicly available on Github repository: https://github.com/ChenShuai00/MAGenIdeas.”

paper: Multi-Agent Iterative Search Boosts LLM Research Idea Novelty and Diversity β€” 2026-04-23
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Has

β€œSource code is available at: https://github.com/ErrEqualsNil/HaS.”

paper: HaS Accelerates RAG via Homology-Based Speculative Retrieval with Minimal Accuracy Loss β€” 2026-04-23
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Conceptframemet

β€œCode, data and statistical scripts are available at https://github.com/julia-nixie/ConceptFrameMet.”

paper: Source Domains and Semantic Frames Jointly Determine Metaphorical Framing Effects β€” 2026-04-23
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Respondeoqa

β€œThe dataset is available at: https://github.com/slanglab/RespondeoQA”

paper: RespondeoQA: First Benchmark for Latin-English Bilingual QA Reveals LLM Weaknesses in Skill-Based Tasks β€” 2026-04-23
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Signdata

β€œCode is available at https://github.com/balaboom123/signdata-slt.”

paper: SignDATA: Configurable Toolkit Standardizes Heterogeneous Sign Language Video Datasets for ML Training β€” 2026-04-23
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Agentpressurebench

β€œOur project page is at https://ucsc-vlaa.github.io/AgentPressureBench .”

paper: User Pressure Drives Coding Agents to Exploit Public Scores Over Genuine Performance β€” 2026-04-23
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Keras Deep Learning Tutorial For Kaggle 2nd Annual Data Science Bowl

β€œKeras Deep Learning Tutorial for Kaggle 2nd Annual Data Science Bowl”

Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Gaoyao

β€œWe release the benchmark (https://github.com/lunyiliu/GaoYao).”

paper: GaoYao Benchmark Overcomes Fragmented, Low-Quality Evaluation of LLMs' Multilingual and Multicultural Capabilities β€” 2026-04-23
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Lexisflow

β€œCode & models will be public at https://anticdimi.github.io/lexis.”

paper: LEXIS-Flow Enables Proximity-Aware 3D HOI Reconstruction from Single Images via Learned Interaction Signatures β€” 2026-04-23
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Marco

β€œCode is available at https://github.com/visinf/MARCO .”

paper: MARCO Achieves SOTA Semantic Correspondence with Superior Generalization in 3x Smaller, 10x Faster Model β€” by Wes Roth β€” 2026-04-23
Endorsed by Wes Roth
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Kimi K26

by @Kimi_Moonshot

β€œOpen weights. Agentic coding that actually finishes.”

tweet: Kimi K2.6 Achieves 185% Throughput Boost Refactoring Legacy Trading Engine Autonomously β€” by Replicate β€” 2026-04-23
Endorsed by Replicate
Details β†’
πŸ’» ReposΓ—1 mentions

Deep Agents Deploy

by LangChain

β€œDeep Agents Deploy: an open alternative to Claude Managed Agents”

blog: Deep Agents Deploy: Open-Source Alternative to Claude Managed Agents for Lock-In-Free Production Deployment β€” by LangChain β€” 2026-04-23
Endorsed by LangChain
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Swyxiodecade

β€œsome more references in footnotes https://www.swyx.io/decade”

tweet: Swyx's X Feed Serves as Hourly Intelligence Poll with Decade References β€” by swyx β€” 2026-04-23
Endorsed by swyx
Details β†’
πŸ’» ReposΓ—1 mentions

Gates Annual Letters

β€œBill'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 do”

Details β†’
πŸ’» ReposΓ—1 mentions

Opinstructhsx

β€œTo facilitate this, we release \textbf{OpInstruct-HSx}, a synthetic dataset of $\approx$28k validated Haskell programs.”

paper: Formal Verification Self-Play in Haskell Boosts LLM Code Reasoning via Semantic Equivalence β€” 2026-04-21
Details β†’
πŸ’» ReposΓ—1 mentions

Modernsasst

β€œOur source code is publicly available on GitHub\footnote{Code is available at: https://github.com/ComplexNetTSP/ST_RUM.”

paper: ModernSASST Pioneers Simplicial Complexes for Efficient High-Order Spatiotemporal Modeling β€” 2026-04-20
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Lightmem

β€œsee https://github.com/zjunlp/LightMem”

paper: StructMem Enables Efficient Structured Memory for Long-Horizon LLM Reasoning β€” 2026-04-25
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Ael

β€œCode and data: https://github.com/WujiangXu/AEL.”

paper: Agent Evolving Learning Unlocks Stateless LLM Agents in Open-Ended Environments via Two-Timescale Memory Use and Reflection β€” 2026-04-25
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Gsquant

β€œOur code is publicly available at https://github.com/mikumifa/GS-Quant.”

paper: GS-Quant Enables Hierarchical Semantic-Structural Quantization for Superior LLM-Based Knowledge Graph Completion β€” 2026-04-25
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Asmrbench

β€œWe release ASMR-Bench to support research on monitoring and auditing techniques for AI-conducted research.”

paper: ASMR-Bench Exposes Weaknesses in AI and Human Auditing of Sabotaged ML Research Code β€” 2026-04-20
Details β†’
πŸ’» ReposΓ—1 mentions

Ramen

β€œOur code is available at https://github.com/baowenxuan/Ramen .”

paper: Ramen Enables Robust Test-Time Adaptation of VLMs in Mixed Domains via Active Sample Retrieval β€” 2026-04-25
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Swnet

β€œThe code is available on GitHub: https://cod-espol.github.io/SWNet/”

paper: SWNet Leverages Cross-Spectral Fusion and Edge Refinement to Excel in Camouflaged Weed Detection β€” 2026-04-20
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Toolattention

β€œThe code for this work is accessible at https://github.com/asadani/tool-attention”

paper: Tool Attention Slashes MCP Tools Tax by 95% via Gated Lazy Schema Loading β€” 2026-04-25
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Groundingmd

β€œHere we propose GROUNDING$.$md, a community-governed, field-scoped epistemic grounding document, using mass spectrometry-based proteomics as an example.”

paper: GROUNDING.md: Field-Scoped Epistemic Documents for Enforcing Validity in Agentic AI Coding β€” 2026-04-25
Details β†’
πŸ’» ReposΓ—1 mentions

Qatie

β€œThe code will be available at https://github.com/GenAI4E/QATIE.git.”

paper: Gated Encoding and Multi-Scale Refinement with QAT Bridge Mobile Image Enhancement Training-Deployment Gap β€” 2026-04-25
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Symtrs

β€œThe results obtained in this work can be reproduced from this Github repository: https://github.com/safouaneelg/SyMTRS.”

paper: SyMTRS: Unified Synthetic Benchmark Enabling Multi-Task Advances in Aerial Depth, Domain Adaptation, and Super-Resolution β€” 2026-04-25
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Maziarkianisemeval2026task9subtask1polarization

β€œCode and final test predictions are publicly available at: https://github.com/Maziarkiani/SemEval2026-Task9-Subtask1-Polarization.”

paper: Language-Adaptive Ensembles Outperform Generalists for Multilingual Polarization Detection in Distinct Scripts β€” 2026-04-25
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Llmbiasbench

β€œWe propose a method, released as the open-source llm-bias-bench”

paper: LLM Bias Bench Reveals Hidden Opinions and Sycophancy Through Coercive Probing β€” 2026-04-25
Details β†’
πŸ’» ReposΓ—1 mentions

Dumo

β€œCode is available at https://github.com/Maplebb/DuMo”

paper: DuMo Enables Precise High-Frequency Concept Erasure in Diffusion Models Without Backbone Alteration β€” by Gong Cha β€” 2026-04-26
Endorsed by Gong Cha
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Maplebbvce

β€œThe code and models are available at https://github.com/Maplebb/VCE.”

paper: VCE Enables Precise Concept Erasure in Autoregressive Image Generators via Contrastive Pairs and DPO β€” by Gong Cha β€” 2026-04-26
Endorsed by Gong Cha
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Sunflower 14b

β€œThese models are open source and can be used to reduce language barriers in a number of important practical applications.”

paper: Sunflower Models Achieve SOTA Comprehension in Most Ugandan Languages via Regional Fine-Tuning β€” by AI Engineer β€” 2026-04-26
Endorsed by AI Engineer
Details β†’
πŸ’» ReposΓ—1 mentions

Sunflower 32b

β€œThese models are open source and can be used to reduce language barriers in a number of important practical applications.”

paper: Sunflower Models Achieve SOTA Comprehension in Most Ugandan Languages via Regional Fine-Tuning β€” by AI Engineer β€” 2026-04-26
Endorsed by AI Engineer
Details β†’
πŸ’» ReposΓ—1 mentions

Online Repository Containing Formalized Proofs

β€œWe also point to an online repository containing formalized proofs of all our results using the lean4 proof assistant”

paper: Modular Pairs Drive New Foundations for Infinite Matroid Theory β€” by Gabe Rivera β€” 2026-04-26
Endorsed by Gabe Rivera
Details β†’
πŸ’» ReposΓ—1 mentions

Unigendet

β€œCode: https://github.com/Zhangyr2022/UniGenDet.”

paper: UniGenDet Unifies Generative and Discriminative Paradigms for Co-Evolving Image Synthesis and Forgery Detection β€” by Charlene Li β€” 2026-04-26
Endorsed by Charlene Li
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Xformers Repo

by Facebook AI

β€œX forers repo has an amazing example of using cud graphs  to achieve no overhead”

Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Lesaudedynamics

β€œSource code is available at https://github.com/cljosegfer/lesaude-dynamics”

paper: Action-Conditioned JEPA Models Cardiac Pathology as Dynamic Transitions, Outperforming Supervised Baselines β€” 2026-04-27
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Planargactivesl

β€œOur code is available at https://github.com/PlanarG/active-sl.”

paper: Active Experiment Selection Cuts Scaling Law Fitting Costs by 90% While Matching Full-Budget Accuracy β€” 2026-04-27
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Llada20uni

β€œCodes and models are available at https://github.com/inclusionAI/LLaDA2.0-Uni.”

paper: LLaDA2.0-Uni Unifies Multimodal Understanding and Generation via Discrete Diffusion LLM β€” by Arvind on AI β€” 2026-04-27
Endorsed by Arvind on AI
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Full Code Walkthrough

β€œFull code + walkthrough: https://t.co/ozm4VwWmj3”

tweet: LlamaIndex Pipeline Automates 40-60% of Loan Processors' Manual Income Reconciliation β€” by LlamaIndex β€” 2026-04-28
Endorsed by LlamaIndex
Details β†’Visit β†—
Page 1 of 79Next β†’