News

AI News Brief — Apr 18

GitHub velocity is led by ggml-org/llama.cpp; paper attention is clustering around GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens; social attention is tilting toward FSF attempts to contact Google about sending more than 10,000 spam emails from Gmail account. 10 repo signals, 10 paper picks, and 10 community items made today's cut.

GitHub velocity is led by ggml-org/llama.cpp; paper attention is clustering around GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens; social attention is tilting toward FSF attempts to contact Google about sending more than 10,000 spam emails from Gmail account. 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
104242 stars · +800/7d · created 1134d ago · updated 1h ago · signal 24.94

ggml-org/llama.cpp

LLM inference in C/C++. Updated 1h ago. 104242 stars, +800/7d, created 1134d ago.

GitHub Repo
147048 stars · +335/7d · created 1164d ago · updated 1h ago · signal 22.53

langflow-ai/langflow

Langflow is a powerful tool for building and deploying AI-powered agents and workflows. Updated 1h ago. 147048 stars, +335/7d, created 1164d ago.

GitHub Repo
92960 stars · +800/7d · created 269d ago · updated 23h ago · signal 24.61

NousResearch/hermes-agent

The agent that grows with you. Updated 23h ago. 92960 stars, +800/7d, created 269d ago.

GitHub Repo
75671 stars · +800/7d · created 369d ago · updated 23h ago · down 1 · signal 24.48

openai/codex

Lightweight coding agent that runs in your terminal. Updated 23h ago. 75671 stars, +800/7d, created 369d ago. Down 1 spots from the previous run.

GitHub Repo
144334 stars · +800/7d · created 352d ago · updated 23h ago · down 1 · signal 24.24

anomalyco/opencode

The open source coding agent. Updated 23h ago. 144334 stars, +800/7d, created 352d ago. Down 1 spots from the previous run.

GitHub Repo
49021 stars · +631/7d · created 904d ago · updated 23h ago · down 2 · signal 20.48

crewAIInc/crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. Updated…

GitHub Repo
59073 stars · +800/7d · created 229d ago · updated 2d ago · down 1 · signal 20.04

thedotmack/claude-mem

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into…

GitHub Repo
183509 stars · +338/7d · created 1128d ago · updated 1h ago · signal 22.14

Significant-Gravitas/AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters. Updated 1h ago. 183509 stars, +338/7…

GitHub Repo
27755 stars · avg 24.2/day · created 1149d ago · updated <1h ago · signal 14.13

labring/FastGPT

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestra…

GitHub Repo
47008 stars · +800/7d · created 13d ago · updated 2d ago · down 2 · signal 21.96

MemPalace/mempalace

The best-benchmarked open-source AI memory system. And it's free. Updated 2d ago. 47008 stars, +800/7d, created 13d ago. Down 2 spots from the previous run.

Top list

Fresh Papers

New research worth bookmarking for a deeper read.

Hugging Face Papers Paper
11h ago · signal 5.57

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

GlobalSplat introduces a global scene representation framework that achieves compact, consistent 3D Gaussian splatting with reduced computational overhead and improved inference speed. Surf…

Hugging Face Papers Paper
14h ago · signal 6.52

DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation

DR$^{3}$-Eval is a benchmark for evaluating deep research agents on multimodal, multi-file report generation, featuring a realistic simulation of web environments and a comprehensive evalua…

Hugging Face Papers Paper
10h ago · signal 6.35

TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification

TRACER is an open-source system that uses production traces to train ML surrogates for LLM classification, activating them only when agreement with the original model exceeds a specified th…

Hugging Face Papers Paper
7h ago · signal 6.29

Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA an…

Corpus2Skill enhances retrieval-augmented generation by structuring document corpora into hierarchical skill directories that enable language model agents to navigate and reason about infor…

Hugging Face Papers Paper
14h ago · signal 6.16

UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards

UniDoc-RL introduces a reinforcement learning framework for LVLMs that jointly optimizes retrieval, reranking, visual perception, and reasoning through hierarchical decision-making and dens…

Hugging Face Papers Paper
3h ago · signal 6.11

Boosting Visual Instruction Tuning with Self-Supervised Guidance

Visual instruction tuning enhanced with naturally phrased self-supervised tasks improves vision-centric reasoning in multimodal language models without additional architecture or annotation…

arXiv Paper
23h ago · signal 5.25

Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines

Fresh arXiv paper from the ai cluster, posted 23h ago.

arXiv Paper
22h ago · signal 5.06

Agentic Microphysics: A Manifesto for Generative AI Safety

Fresh arXiv paper from the ai cluster, posted 22h ago.

arXiv Paper
1d ago · signal 4.34

MCSC-Bench: Multimodal Context-to-Script Creation for Realistic Video Production

Fresh arXiv paper posted 1d ago and surfacing in the current feed.

arXiv Paper
1d ago · signal 4.63

Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching

Fresh arXiv paper from the ai cluster, posted 1d ago.

Today in AI

The day in one pass

GitHub velocity is led by ggml-org/llama.cpp; paper attention is clustering around GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens; social attention is tilting toward FSF attempts to contact Google about sending more than 10,000 spam emails from Gmail account. 10 repo signals, 10 paper picks, and 10 community items made today's cut.

The quickest scan starts with ggml-org/llama.cpp, GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens, and €54,000 bill surge in 13 hours: Gemini API calls made with Firebase browser keys without API re…, 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

2026-04-18 AI News Brief — 2026-04-18 GitHub velocity is led by ggml-org/llama.cpp; paper attention is clustering around GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens; social attention is tilting toward FSF attempts to contact Google about sending more than 10,000 spam emails from Gmail account. 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-04-17 AI News Brief — 2026-04-17 GitHub velocity is led by ray-project/ray; paper attention is clustering around SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments; social attention is tilting toward With Swagger, AI creates the entire frontend. Swagger is the best context and harness.; biggest mover: openai/codex (+3). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-04-16 AI News Brief — 2026-04-16 GitHub velocity is led by badlogic/pi-mono; paper attention is clustering around Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic…; social attention is tilting toward OpenAI unveils ‘Trusted Access’ expansion strategy for cyber defense and GPT-5.4 Cyber; biggest mover: badlogic/pi-mono (+7). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-04-15 AI News Brief — 2026-04-15 GitHub velocity is led by shanraisshan/claude-code-best-practice; paper attention is clustering around Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Genera…; social attention is tilting toward damn-my-slow-kt - KT Internet SLA failure automatic measurement & fee reduction application tool; biggest mover: NVIDIA/NemoClaw (+3). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-04-14 AI News Brief — 2026-04-14 GitHub velocity is led by MemPalace/mempalace; paper attention is clustering around EXAONE 4.5 Technical Report; social attention is tilting toward Concerns about the open source community after Vibe coding; biggest mover: HKUDS/CLI-Anything (+7). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-04-13 AI News Brief — 2026-04-13 GitHub velocity is led by affaan-m/everything-claude-code; paper attention is clustering around DeonticBench: A Benchmark for Reasoning over Rules; social attention is tilting toward Introducing Muse Spark, the first in the Muse family of models developed by Meta Superintellige…; biggest mover: affaan-m/everything-claude-code (+5). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-04-12 AI News Brief — 2026-04-12 GitHub velocity is led by openai/codex; paper attention is clustering around Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models; social attention is tilting toward OpenAI's Support for Illinois AI Liability Limitation Legislation; biggest mover: sickn33/antigravity-awesome-skills (+33). 10 repo signals, 10 paper picks, and 10 community items made today's cut. 2026-04-11 AI News Brief — 2026-04-11 GitHub velocity is led by BerriAI/litellm; paper attention is clustering around Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models; social attention is tilting toward Show GN: Advisor Opus — Implementing Anthropic’s Advisor Strategy with Claude Code plugin; biggest mover: NVIDIA/NemoClaw (+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 Apr 18, 2026 as one single daily issue.