AI Open Source

Perplexity Opens Up Its Skills Design Core

Perplexity open sources Skills design. Best practices for LLMs not code.

May 17 • Meng Li

Gemma 4 Delivers 3x Speedup, Day 0 Support for vLLM

Google Gemma 4 now runs 3x faster with MTP Drafter. Day 0 vLLM support, 2B–31B models, no quality loss.

May 7 • Meng Li

The Single-Agent Era Is Over: One Fails, Use 300

Kimi K2.6 launches Agent Swarm with 300 sub Agents. Coding and collaboration now outperform GPT 5.4.

Apr 21 • Meng Li

Get Started with Hermes Agent Right Away

Hermes Agent vs OpenClaw: better long-term evolution, low-cost VPS deployment, OpenAI API compatible, one-curl install.

Apr 13 • Meng Li

Claude Bans OpenClaw

Claude bans OpenClaw, raises costs, and pushes users to paid APIs. Open source AI tools face a platform crackdown.

Apr 5 • Meng Li

Two Popular Apps Poisoned in One Week – Don’t Fall Victim!

Two supply chain attacks hit Apifox and LiteLLM. Check if you're affected and rotate credentials now.

Mar 26 • Meng Li

One Command to Turn Any Code Repository into a Learnable Course

Vibe coding leaving you lost in your own code? Codebase-to-Course turns any repo into a clear, interactive HTML tutorial using Claude Code Skills…

Mar 26 • Meng Li

600K Lines, 60 Days: The Method Is Now Open Source

A powerful open-source toolkit for Claude Code that doubles QA capacity, syncs documentation, and enables seamless AI-agent collaboration with browser…

Mar 23 • Meng Li

The Smarter OpenClaw Gets! What Skills Have I Installed?

Discover the essential OpenClaw and NanoClaw Skills that make your lobster smarter.

Mar 16 • Meng Li

Uninstall OpenClaw! Embrace NanoClaw

Discover why AI expert Karpathy praises NanoClaw's revolutionary approach.

Feb 26 • Meng Li

You Probably Don't Need OpenClaw! A Story from My Real Need

OpenClaw hype vs reality: why you probably don't need it. Real user pain points, security flaws, and a smarter alternative for AI agent tasks.

Feb 23 • Meng Li

Qwen3.5 Local Deployment

Deploy Qwen3.5 397B locally with Unsloth Dynamic 2.0 quantization. Run on Mac or PC with llama.cpp, SGLang, MLX, and OpenAI compatible API.

Feb 17 • Meng Li

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts