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.
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.
ggml-org/llama.cpp
LLM inference in C/C++. Updated 1h ago. 104242 stars, +800/7d, created 1134d ago.
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.
NousResearch/hermes-agent
The agent that grows with you. Updated 23h ago. 92960 stars, +800/7d, created 269d ago.
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.
anomalyco/opencode
The open source coding agent. Updated 23h ago. 144334 stars, +800/7d, created 352d ago. Down 1 spots from the previous run.
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…
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…
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…
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…
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.
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…
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…
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…
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…
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…
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…
Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
Fresh arXiv paper from the ai cluster, posted 23h ago.
Agentic Microphysics: A Manifesto for Generative AI Safety
Fresh arXiv paper from the ai cluster, posted 22h ago.
MCSC-Bench: Multimodal Context-to-Script Creation for Realistic Video Production
Fresh arXiv paper posted 1d ago and surfacing in the current feed.
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.
Archive
Recent issues
Generated from the ranked feed for Apr 18, 2026 as one single daily issue.
Linked Mentions
No linked mentions yet.