News
AI News Brief — May 25
GitHub velocity is led by NousResearch/hermes-agent; paper attention is clustering around ACC: Compiling Agent Trajectories for Long-Context Training; social attention is tilting toward Is AI still profitable?; biggest mover: ruvnet/ruflo (+3). 10 repo signals, 10 paper picks, and 10 community items made today's cut.
GitHub velocity is led by NousResearch/hermes-agent; paper attention is clustering around ACC: Compiling Agent Trajectories for Long-Context Training; social attention is tilting toward Is AI still profitable?; biggest mover: ruvnet/ruflo (+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.
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.
NousResearch/hermes-agent
The agent that grows with you. Updated 1h ago. 165284 stars, +800/7d, created 306d ago. Up 1 spots from the previous run.
openai/codex
Lightweight coding agent that runs in your terminal. Updated 1h ago. 85130 stars, +800/7d, created 406d ago.
ruvnet/ruflo
🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade…
Hmbown/CodeWhale
Coding agent for open source, open weight models. Updated 1h ago. 34143 stars, +800/7d, created 125d ago.
anomalyco/opencode
The open source coding agent. Updated 1h ago. 164658 stars, +800/7d, created 389d ago. Up 2 spots from the previous run.
ggml-org/llama.cpp
LLM inference in C/C++. Updated 1h ago. 112664 stars, +800/7d, created 1171d ago.
ZhuLinsen/daily_stock_analysis
LLM-powered stock analysis system for A/H/US markets: multi-data source market + real-time news + LLM decision-making dashboard + multi-channel push, zero-cost scheduled operation, pure fre…
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. 53528 stars, +800/7d, created 122d ago. Up 2 spots from…
MemPalace/mempalace
The best-benchmarked open-source AI memory system. And it's free. Updated 1h ago. 52762 stars, +464/7d, created 50d ago. Up 2 spots from the previous run.
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. 18876 stars, avg 26.8/day, created 704d ago.
Top list
Fresh Papers
New research worth bookmarking for a deeper read.
ACC: Compiling Agent Trajectories for Long-Context Training
Agent Context Compilation (ACC) enhances long-context reasoning in LLMs by converting multi-turn agent trajectories into structured QA pairs, enabling direct supervision of distant context…
Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
A reinforcement learning-driven orchestration framework dynamically composes expert models and skills for multimodal tasks, achieving superior performance with low computational overhead. S…
Bernini: Latent Semantic Planning for Video Diffusion
A unified video generation and editing framework combines multimodal large language models for semantic planning with diffusion models for pixel rendering, achieving state-of-the-art perfor…
Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
Lean Refactor presents a retrieval-augmented agentic framework that improves Lean proof refactoring by addressing multi-objective optimization, version compatibility, and scalability challe…
OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
OmniPro is introduced as the first benchmark for evaluating omni-modal large language models' proactive streaming video understanding, featuring diverse tasks and dual-mode evaluation proto…
Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion M…
Audio diffusion models are adapted for interactive music generation through efficient block-wise processing and novel training paradigms that enable real-time performance on consumer hardwa…
TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
TransitLM dataset enables end-to-end transit route planning using large language models trained on structured transit data, eliminating the need for traditional map-based approaches. Surfac…
Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study
Fresh arXiv paper from the ai cluster, posted 3d ago. Down 154 spots from the previous run.
Forecasting Scientific Progress with Artificial Intelligence
Current AI systems demonstrate limited capability in predicting scientific progress, showing inconsistent performance across domains and systematic overconfidence in forecasts. Surfaced via…
An intensive vRAN deployment with OpenAirInterface
Fresh arXiv paper posted 3d ago and surfacing in the current feed. Down 165 spots from the previous run.
Today in AI
The day in one pass
GitHub velocity is led by NousResearch/hermes-agent; paper attention is clustering around ACC: Compiling Agent Trajectories for Long-Context Training; social attention is tilting toward Is AI still profitable?; biggest mover: ruvnet/ruflo (+3). 10 repo signals, 10 paper picks, and 10 community items made today's cut.
The quickest scan starts with NousResearch/hermes-agent, ACC: Compiling Agent Trajectories for Long-Context Training, and Hancom supplies AI agent to LG ‘ChatExaOne’, 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.
Archive
Recent issues
Generated from the ranked feed for May 25, 2026 as one single daily issue.