← all editions
EDITION 41 · SKILLS SURGE: NATURE-SKILLS LEADS, COLIBRI RUNS 744B ON 25GB2026·07·115 min readlinks verified live

Skills surge: nature-skills leads, Colibri runs 744B on 25GB

We don't tell you what's popular — popularity lags and is gameable. We tell you what's gaining speed right now, and whether it's worth your attention. 6 accelerating AI repos earned today's slot.

↑284/day
fastest climber
in the edition
6
picks that
earned a slot
live
counts pulled
at publish
5min
to read the
whole edition
01

Top mover

★ TOP MOVER
Yuan1z0825/nature-skillsWATCHPython▲ 284 /day★ 27,714

This repo provides a curated set of skills (prompts/templates) for generating Nature-level academic text and scientific figures using Codex or similar LLMs. It's gaining traction because researchers want to streamline manuscript preparation and achieve publication-quality visuals without manual formatting. However, it's essentially a prompt library, not a tool—results depend heavily on the underlying model and user input.

3mo oldApache-2.01.7k forksactive 1d ago0 open issues
Competes withOverleaf templates, LaTeX packages
Who needs itAcademic researchers and scientific writers
02

🤖 Agents & automation

microsoft/SkillOptUSEPython▲ 223 /day★ 12,128

SkillOpt optimizes natural-language skills for frozen LLM agents by editing trajectories and validating updates, enabling self-evolving agents without retraining. It's gaining traction because it addresses the key challenge of improving agent performance efficiently. A caveat: the skill optimization may overfit to specific trajectories, limiting generalization.

2mo oldMIT1.1k forksactive 8d ago36 open issues
Competes withLangChain
Who needs itDevelopers building LLM agents
davidondrej/skillsWATCH▲ 140 /day★ 2,248

This repo provides a structured way to define and share personal AI agent skills, enabling modular, reusable capabilities for agents. It's gaining traction because it simplifies building custom agent behaviors without heavy frameworks. However, it's early-stage and may lack production robustness.

17d oldMIT263 forksactive 1d ago2 open issues
Competes withLangChain tools
Who needs itDevelopers building personal AI agents
03

⚙️ Inference & serving

JustVugg/colibriWATCHC▲ 267 /day★ 2,406

Colibri enables inference of the massive GLM-5.2 (744B MoE) model on consumer hardware by streaming experts from disk, using pure C with zero dependencies. This matters because it dramatically lowers the hardware barrier for running state-of-the-art MoE models, but the trade-off is slower inference due to disk I/O and limited to single-batch processing.

10d oldApache-2.0171 forksactive 14h ago13 open issues
Competes withllama.cpp
Who needs itDevelopers running large MoE models on limited hardware
04

Tooling & infra

EvanBacon/serve-simUSETypeScript▲ 118 /day★ 2,406

This tool lets you run Apple iOS simulators headlessly and serve them via HTTP, enabling CI/CD testing and agent-based automation without a GUI. It's gaining traction because it fills a gap for developers needing to automate iOS testing in cloud or headless environments, similar to how npx serve simplifies local web serving. A caveat: it relies on Apple's simulator infrastructure, so it only works on macOS and may have stability issues with complex app interactions.

2mo oldApache-2.0122 forksactive 2d ago31 open issues
Competes withXcode's simctl
Who needs itiOS developers automating CI/CD or agent workflows
virgiliojr94/book-to-skillUSEPython▲ 99 /day★ 8,434

This tool converts technical book PDFs into structured skill files for Claude Code, enabling developers to query and reference book content directly in their coding workflow. It's gaining traction because it bridges the gap between static PDF knowledge and interactive AI-assisted development, but it depends on the quality of the PDF's text extraction and may not handle complex layouts or scanned pages well.

2mo oldMIT1k forksactive 7d ago8 open issues
Who needs itDevelopers using Claude Code who want to integrate book knowledge

Catch the next breakout before it trends.

The fastest-accelerating open-source AI, curated and called. A fresh read every day. Free.

Join 8,400+ engineers · free · no spam
Almost there — check your inbox and click the confirmation link to finish.