Back to home

GitHub

23 articles tagged with this topic

PPT Masterfrontend-slides

AI PPT Solutions Diverge Wildly — Two 67k-Star GitHub Projects Pick Sides

PPT Master (41k stars) outputs native Office; frontend-slides (26k stars) ships HTML. Two Claude Code Skills, opposite bets on AI's white-collar futur

13h ago2 min read
OCamlrclone

AI Spots Bugs in 10 Minutes — Open Source's 30-Year Embargo Must Be Rebuilt

AI coding assistants shrink vulnerability discovery from days to 10 minutes, breaking open source's decades-old embargo. Maintainers and enterprises m

1d ago2 min read
GitHubClaude Code

22.8K-Star SKILL.md: AI's Real Problem Isn't Stupidity—It's Talking Too Much

i-have-adhd hit 22.8K GitHub Stars by teaching Coding Agents to lead with answers via SKILL.md. Lesson: AI's UX problem is verbosity, not stupidity.

1d ago2 min read
AI testingAI application evaluation

Testers Become AI Quality Inspectors: Open-Source Roadmap Exposes a Talent Gap

A 13-chapter AI testing roadmap hit GitHub, gaining thousands of stars. Real signal: "who verifies AI" is becoming a new job.

1d ago2 min read
YOLOopen-source

Local AI Cuts Basketball Edits From 2 Hours to 30 Minutes

A basketball fan built a free YOLO-based tool cutting 2-3 hours of manual highlight editing to 30 minutes — no cloud AI required.

3d ago2 min read
AI AgentClaude Code

AI Agent Demo Is Step One — Six Engineering Pieces to Production

Taking an AI agent from demo to enterprise production needs six engineering pieces — more practical and underrated than swapping in a stronger model.

4d ago2 min read
GCHQGitHub

GCHQ Agent Impersonated Multiple Maintainers—Open Source Review Is Repriced

Autonomous agents recon, poison, impersonate identities, and sustain pressure. Passing tests doesn't mean submitters are trustworthy—open source trust

5d ago2 min read
lw.MD简墨

He Goes Local in the AI Era: One EXE Packs a Full Markdown Editor

Developer lw ships lw.MD (简墨), a single-EXE, zero-install Windows Markdown editor—no cloud, no AI, a contrarian bet in the AI-writing era.

Aug 222 min read
Ragentnageoffer

Ragent 1.1.0 Ships: A Chinese Developer's RAG Framework Goes Enterprise-Grade

Ragent 1.1.0 ships from a solo Chinese dev. What was 'runnable' becomes 'auditable': four-channel hybrid retrieval, source attribution, tiered routing

Aug 192 min read
claude-videoBrad Bonanno

Claude Watches Videos Now: 15,000 Stars Show Indie Devs Patching AI Gaps

Brad Bonanno's /watch command lets Claude read YouTube and local videos—15,200 GitHub Stars in. Indie devs are grabbing AI's last-mile problem.

Aug 182 min read
GitHubOpen Source

24,000 eBooks Open-Sourced on GitHub — When Sharing Hits the Copyright Wall

GitHub repo bundles 24,000 Chinese eBook download links from paid platforms, open-source. Massive scale meets copyright—the same fault line as AI trai

Aug 182 min read
DeepSeekHarness

DeepSeek Open-Sources Lego-Like Agent Framework; 50K Stars Show Developer Hunger

DeepSeek's Harness Agent framework hit 50K GitHub stars in days. Everything is a plugin — models, tools, skills as Lego-like pieces for AI workflows.

Aug 142 min read
GitHubSimon Willison

GitHub Quietly Retires Its Model Service — The Free AI Coding Lunch Is Over

GitHub has silently shut down GitHub Models without explanation. Even Microsoft's own subsidiary can't stomach AI coding costs anymore — free API pipe

Aug 102 min read
GitHubClaude Code

GitHub’s July Shift: Skills Surge as AI Competition Moves to the Shell

GitHub’s July trends show Skills becoming open source AI’s hottest category as competition shifts from models to protocols, tooling, and runtime shell

Jul 162 min read
BeeWeaveZhihu

BeeWeave Turns One Writing Task Into the Starting Point for the Next

BeeWeave’s real value is not AI writing, but turning materials, workflow, style, and traceability into one compounding workspace.

Jul 162 min read
DeepSeekDeepSeek-TUI

DeepSeek-TUI Tops GitHub at 2434 Stars: Terminal AI Agent Goes Practical

Terminal AI agent DeepSeek-TUI installs in 15s, supports MCP & sub-agents. Terminal AI crosses from "works" to "works well"; Chinese LLMs now compete

May 62 min read
GitHubWhisper

Local Voice Agent Tutorial on GitHub Solves Privacy and Latency Without Cloud

A 9-chapter GitHub tutorial builds a fully local voice agent, proving offline low-latency conversation works—new path for compliant enterprise voice A

May 32 min read
Hermes AgentObsidian

Free Hermes Agent-Obsidian Sync: AI Knowledge Bases Break Free from Chatboxes

Hermes Agent's LLM Wiki auto-extracts concepts and syncs to local Obsidian. AI shifts from passive Q&A to proactive curation, making personal KM a new

May 32 min read
GitHubhermes-agent

GitHub April 2026 Trending: AI Shifts from Hype to Production Readiness

GitHub's April 2026 trending shows AI Agents shifting to collaboration and retention. hermes-agent leads with 129K Stars. The PoC era is officially ov

May 22 min read
Matt PocockClaude Code

21 Markdowns, 50K Stars: Matt Pocock Proves AI Coding Needs No Big Frameworks

Matt Pocock's 21 AI coding Skills hit GitHub Trending #1 (49.8K stars). Signal: engineers reject all-in-one AI frameworks, returning to small, composa

May 12 min read
GitHubSecurity Vulner ability

Your repo could be remotely hij acked — GitHub bug fixed , 10 -min check

GitHub fixed a critical bug allowing remote code execution via automation . Check Actions permissions in 10 mins to secure client

Apr 282 min read
Claude CodeAnthropic

AI 自动值夜班时代来了!Claude Code 刚刚推出 Routines

Anthropic releases Claude Code Routines in research preview, enabling scheduled and event-driven autonomous coding tasks on Anthropic's cloud infrast

Apr 152 min read
GitHubGitHub Actions

Quoting Kyle Daigle

GitHub CO O reports 275M weekly commits and 2.1B Actions minutes, signaling AI -driven dev activity surge.

Apr 92 min read