Mud's Blog
← Home

2026-09-28 · news · news / news-brief / ai / radar

AI News Brief — Sep 28

News

AI News Brief — Sep 28

GitHub velocity is led by NousResearch/hermes-agent; paper attention is clustering around MemoryAthena: Adaptive Routing over Latent and Generated Memories; social attention is tilting toward OpenAI researcher, “It would be a problem if Hacker News found out about the use of pirated boo… 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 MemoryAthena: Adaptive Routing over Latent and Generated Memories; social attention is tilting toward OpenAI researcher, “It would be a problem if Hacker News found out about the use of pirated boo… 10 repo signals, 10 paper picks, and 10 community items made today's cut. The lead read pulls the strongest repo, paper, and community items into one skimmable pass.

Source data Digest archive Monthly archive
Issue date
Generated
Signals 10 repos · 10 papers

Daily Brief

Today’s read list

GitHub velocity is led by NousResearch/hermes-agent; paper attention is clustering around MemoryAthena: Adaptive Routing over Latent and Generated Memories; social attention is tilting toward OpenAI researcher, “It would be a problem if Hacker News found out about the use of pirated boo… 10 repo signals, 10 paper picks, and 10 community items made today's cut.

Lead read

AI News Brief — Sep 28

GitHub velocity is led by NousResearch/hermes-agent; paper attention is clustering around MemoryAthena: Adaptive Routing over Latent and Generated Memories; social attention is tilting toward OpenAI researcher, “It would be a problem if Hacker News found out about the use of pirated boo… 10 repo signals, 10 paper picks, and 10 community items made today's cut. The lead read pulls the strongest repo, paper, and community items into one skimmable pass.

GH NousResearch/hermes-agent GitHub · 218.2k stars HF MemoryAthena: Adaptive Routing over Latent and Generated Memories HF Papers · 4d ago paper

Repo momentum

Repository Momentum

Fresh GitHub projects worth scanning before the feed turns over.

GitHub NousResearch/hermes-agent The agent that grows with you. Updated 68d ago. 218250 stars, +800/7d, created 432d ago. 218.2k stars +800/7d · created 432d ago · updated 68d ago GitHub BerriAI/litellm The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenA… 54.1k stars +714/7d · created 1159d ago · updated 69d ago GitHub headroomlabs-ai/headroom Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server. Upd… 60.6k stars +800/7d · created 263d ago · updated 70d ago GitHub shanraisshan/claude-code-best-practice from vibe coding to agentic engineering - practice makes claude perfect. Updated 70d ago. 63155 stars, +674/7d, created 331d ago. 63.2k stars +674/7d · created 331d ago · updated 70d ago GitHub warpdotdev/warp Warp is an agentic development environment, born out of the terminal. Updated 69d ago. 63462 stars, +383/7d, created 1907d ago. 63.5k stars +383/7d · created 1907d ago · updated 69d ago GitHub huggingface/transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. Updated 74d ago.… 162.6k stars +296/7d · created 2890d ago · updated 74d ago

Paper queue

Fresh Papers

New research worth bookmarking for a deeper read.

HF Papers MemoryAthena: Adaptive Routing over Latent and Generated Memories Learned-memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be modified independently. We study whet… 4d ago paper HF Papers Agent-Editing World Model: Rethinking World Modeling for LLM Agents Recent advances in large language models (LLMs) have enabled agents to tackle long-horizon tasks across diverse environments. To further improve agent performance, existing language world m… 3d ago paper HF Papers Training Object Permanence in World Models Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that video generation models, a paradigmatic class of current world models, have begun to show em… 3d ago paper HF Papers All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation Video is a rich representation of a physical event, capturing appearance, geometry, motion, and temporal evolution. Other modalities, such as 3D body motion or audio, encode narrower aspect… 4d ago paper HF Papers Rufus-Air: An Open LLM Post-Training Recipe Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Followi… 3d ago paper HF Papers OmniEcho: Spatial Audio Understanding for Embodied Agents Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challenging for embodied agents. In particular, it is stil… 3d ago paper

Editor note

Repo: NousResearch/hermes-agent (GitHub and 68d ago) 30 curated items made this issue; the source mix below shows where today’s brief came from.

Today in AI

The day in one pass

GitHub velocity is led by NousResearch/hermes-agent; paper attention is clustering around MemoryAthena: Adaptive Routing over Latent and Generated Memories; social attention is tilting toward OpenAI researcher, “It would be a problem if Hacker News found out about the use of pirated boo… 10 repo signals, 10 paper picks, and 10 community items made today's cut.

The quickest scan starts with NousResearch/hermes-agent, MemoryAthena: Adaptive Routing over Latent and Generated Memories, and OpenAI researcher, “It would be a problem if Hacker News found out about the use of pirated boo…, while 10 GitHub-led signals anchor the repo side of the brief.

The sections below keep the longer tail available without crowding the lead read.

Wire

Community Chatter

Directional signals from discussion-heavy sources.

Archive

Recent issues

2026-09-28 AI News Brief — 2026-09-28 GitHub velocity is led by NousResearch/hermes-agent; paper attention is clustering around MemoryAthena: Adaptive Routing over Latent and Generated Memories; social attention is tilting toward OpenAI researcher, “It would be a problem if Hacker News found out about the use of pirated boo… 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-09-27 AI News Brief — 2026-09-27 Today's AI landscape highlights significant activity in agent development on GitHub, novel memory system research, and community discussion around Meta's Muse model. 2026-09-26 AI News Brief — 2026-09-26 Today's AI landscape highlights significant activity in agentic models, with new research focusing on world modeling and practical applications gaining traction across GitHub and academic papers. 2026-09-25 AI News Brief — 2026-09-25 GitHub velocity is led by vllm-project/vllm; paper attention is clustering around MemoryAthena: Adaptive Routing over Latent and Generated Memories; social attention is tilting toward Australian Prime Minister says OpenAI agent hacked Australian government website. 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-09-24 AI News Brief — 2026-09-24 Today's AI landscape sees significant activity in agentic systems, led by NousResearch's Hermes, alongside notable advancements in universal omni-modal embeddings and discussions around AI company public relations. 2026-09-23 AI News Brief — 2026-09-23 Today's AI landscape highlights significant activity in agent development, new research on recursive self-improvement, and a notable breakthrough in historical decryption by OpenAI's GPT-6 Astra. 2026-09-22 AI News Brief — 2026-09-22 GitHub velocity is led by NousResearch/hermes-agent; paper attention is clustering around Learning Foresight without Explicit Trajectories for 3D Diffusion Policies; social attention is tilting toward AI chatbot gives ‘most’ incorrect answers to financial questions. 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-09-21 AI News Brief — 2026-09-21 Today's AI landscape is marked by continued momentum in agentic AI development on GitHub and new research exploring gaze as evidence for common grounding.
Browse the monthly archive

Generated from the curated feed for Sep 28, 2026 as one daily issue.