← Home

2026-05-18 · news · news / news-brief / ai / radar

AI News Brief — May 18

News

AI News Brief — May 18

GitHub velocity is led by affaan-m/everything-claude-code; paper attention is clustering around RewardHarness: Self-Evolving Agentic Post-Training; social attention is tilting toward Elon Musk, after contract to acquire Cursor, “plans to train Grok V9 with Cursor data”; biggest mover: rtk-ai/rtk (+3). 10 repo signals, 10 paper picks, and 10 community items made today's cut.

GitHub velocity is led by affaan-m/everything-claude-code; paper attention is clustering around RewardHarness: Self-Evolving Agentic Post-Training; social attention is tilting toward Elon Musk, after contract to acquire Cursor, “plans to train Grok V9 with Cursor data”; biggest mover: rtk-ai/rtk (+3). 10 repo signals, 10 paper picks, and 10 community items made today's cut. This fallback brief keeps the page live when the optional Gemma pass times out.

Issue date
Generated
Signals 10 repos · 10 papers

Signal Board

Repositories and papers

Keep the full repo and paper scan above the fold, then read the day as one short brief below.

Top list

Repository Momentum

Fresh GitHub projects worth scanning before the feed turns over.

GitHub Repo
185393 stars · +800/7d · created 120d ago · updated 1h ago · up 1 · signal 24.69

affaan-m/everything-claude-code

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. Updated 1h ago. 1…

GitHub Repo
83253 stars · +800/7d · created 399d ago · updated 1h ago · signal 26.30

openai/codex

Lightweight coding agent that runs in your terminal. Updated 1h ago. 83253 stars, +800/7d, created 399d ago.

GitHub Repo
154334 stars · +800/7d · created 299d ago · updated 4h ago · up 1 · signal 26.29

NousResearch/hermes-agent

The agent that grows with you. Updated 4h ago. 154334 stars, +800/7d, created 299d ago. Up 1 spots from the previous run.

GitHub Repo
141664 stars · +800/7d · created 1131d ago · updated 1h ago · signal 25.18

langgenius/dify

Production-ready platform for agentic workflow development. Updated 1h ago. 141664 stars, +800/7d, created 1131d ago.

GitHub Repo
110585 stars · +800/7d · created 1164d ago · updated 1h ago · down 3 · signal 24.71

ggml-org/llama.cpp

LLM inference in C/C++. Updated 1h ago. 110585 stars, +800/7d, created 1164d ago. Down 3 spots from the previous run.

GitHub Repo
94977 stars · +800/7d · created 1029d ago · updated 1h ago · signal 17.76

rasbt/LLMs-from-scratch

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. Updated 1h ago. 94977 stars, +800/7d, created 1029d ago.

GitHub Repo
49205 stars · +800/7d · created 115d ago · updated 1h ago · up 3 · signal 20.95

rtk-ai/rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies. Updated 1h ago. 49205 stars, +800/7d, created 115d ago. Up 3 spots from…

GitHub Repo
18732 stars · avg 26.9/day · created 697d ago · updated <1h ago · signal 11.86

screenpipe/screenpipe

YC (S26) | Give AI the ability to live your experience. Records everything you do, say, hear 24/7, local, private, secure. Updated <1h ago. 18732 stars, avg 26.9/day, created 697d ago.

GitHub Repo
5478 stars · avg 3.7/day · created 1483d ago · updated <1h ago · signal 11.54

Eventual-Inc/Daft

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale. Updated <1h ago. 5478 stars, avg 3.7/day, created 1483d ago.

GitHub Repo
52360 stars · +603/7d · created 43d ago · updated 1h ago · signal 23.16

MemPalace/mempalace

The best-benchmarked open-source AI memory system. And it's free. Updated 1h ago. 52360 stars, +603/7d, created 43d ago.

Top list

Fresh Papers

New research worth bookmarking for a deeper read.

HF Papers Paper
3d ago · signal 4.65

RewardHarness: Self-Evolving Agentic Post-Training

RewardHarness is a self-evolving framework that improves image edit evaluation by iteratively developing tools and skills from limited human demonstrations, achieving superior performance c…

HF Papers Paper
3d ago · signal 4.39

FutureSim: Replaying World Events to Evaluate Adaptive Agents

FutureSim enables evaluation of AI agents' long-term predictive capabilities by simulating chronological real-world event sequences, revealing significant gaps in current forecasting perfor…

HF Papers Paper
3d ago · down 129 · signal 4.38

Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Mo…

The Darwin Family framework enables training-free evolutionary merging of large language models through gradient-free weight-space recombination, achieving superior reasoning performance wi…

HF Papers Paper
3d ago · signal 4.33

Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning

Adaptive Teacher Exposure for Self-Distillation (ATESD) improves large language model reasoning by dynamically adjusting teacher exposure during training through a learnable policy controll…

HF Papers Paper
3d ago · signal 4.31

ViMU: Benchmarking Video Metaphorical Understanding

Video understanding models lack capability to interpret implicit meanings and social contexts beyond literal visual comprehension, necessitating new benchmarking approaches. Surfaced via Hu…

HF Papers Paper
3d ago · down 136 · signal 4.27

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

MemEye framework evaluates multimodal agent memory by measuring visual evidence granularity and retrieval usage complexity across 8 life-scenario tasks. Surfaced via HF Papers 3d…

HF Papers Paper
3d ago · signal 4.22

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interac…

A novel causal consistency distillation method enables efficient frame-wise video generation with reduced latency and improved quality compared to existing chunk-wise approaches. Surfaced v…

HF Papers Paper
3d ago · signal 4.16

Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthe…

Self-improving language models construct environments for training rather than generating data, utilizing stable solve-verify asymmetry to maintain informative rewards during learning. Surf…

HF Papers Paper
3d ago · signal 3.87

Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolutio…

Multi-agent systems face challenges in sustained coordination and error propagation, requiring integrated approaches that enable continuous diagnosis, reorganization, and behavioral refinem…

HF Papers Paper
3d ago · signal 4.05

Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video

A novel approach called Warp-as-History enables camera-controlled video generation by transforming camera-induced warps into pseudo-history representations, achieving zero-shot capability w…

Today in AI

The day in one pass

GitHub velocity is led by affaan-m/everything-claude-code; paper attention is clustering around RewardHarness: Self-Evolving Agentic Post-Training; social attention is tilting toward Elon Musk, after contract to acquire Cursor, “plans to train Grok V9 with Cursor data”; biggest mover: rtk-ai/rtk (+3). 10 repo signals, 10 paper picks, and 10 community items made today's cut.

The quickest scan starts with affaan-m/everything-claude-code, RewardHarness: Self-Evolving Agentic Post-Training, and The Uselessness of Lava Lamps: What Random Really Means, while 10 GitHub-led signals anchor the repo side of the brief.

Use the structured digest below when you need the full wire, raw links, and the longer tail of items that did not make the front narrative.

Wire

Community Chatter

Directional signals from discussion-heavy sources.

Archive

Recent issues

2026-05-18 AI News Brief — 2026-05-18 GitHub velocity is led by affaan-m/everything-claude-code; paper attention is clustering around RewardHarness: Self-Evolving Agentic Post-Training; social attention is tilting toward Elon Musk, after contract to acquire Cursor, “plans to train Grok V9 with Cursor data”; biggest mover: rtk-ai/rtk (+3). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-05-17 AI News Brief — 2026-05-17 GitHub velocity is led by ggml-org/llama.cpp; paper attention is clustering around WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild; social attention is tilting toward What does GGUF contain besides weights, and what is still missing? 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-05-16 AI News Brief — 2026-05-16 GitHub velocity is led by shanraisshan/claude-code-best-practice; paper attention is clustering around MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models; social attention is tilting toward How to tune ZFS for random access workloads; biggest mover: safishamsi/graphify (+8). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-05-15 AI News Brief — 2026-05-15 GitHub velocity is led by langgenius/dify; paper attention is clustering around Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling; social attention is tilting toward Lessons learned from inside China’s AI lab; biggest mover: MemPalace/mempalace (+2). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-05-14 AI News Brief — 2026-05-14 GitHub velocity is led by open-webui/open-webui; paper attention is clustering around SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture; social attention is tilting toward Needle - 26 million parameter model distilled from Gemini tool calls.; biggest mover: sickn33/antigravity-awesome-skills (+19). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-05-13 AI News Brief — 2026-05-13 GitHub velocity is led by ruvnet/ruflo; paper attention is clustering around TMAS: Scaling Test-Time Compute via Multi-Agent Synergy; social attention is tilting toward UCLA discovers first stroke rehabilitation drug to repair brain damage (2025); biggest mover: antirez/ds4 (+7). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-05-12 AI News Brief — 2026-05-12 GitHub velocity is led by openai/codex; paper attention is clustering around LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling; social attention is tilting toward Ask GN: What do you think about services that involve human intervention in an environment wher…; biggest mover: affaan-m/everything-claude-code (+9). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-05-11 AI News Brief — 2026-05-11 GitHub velocity is led by warpdotdev/warp; paper attention is clustering around GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs; social attention is tilting toward AlphaEvolve: Gemini-based coding agent expanding influence across multiple sectors; biggest mover: ZhuLinsen/daily_stock_analysis (+2). 10 repo signals, 10 paper picks, and 10 community items made today's cut.
Browse the monthly archive

Generated from the ranked feed for May 18, 2026 as one single daily issue.