walkinglabs

@goyalshaliniuk Excellent, thank you 🤗 walkinglabs/learn-harness-engineering

این دوره بر پایه مقالات مهندسی OpenAI و Anthropic درباره طراحی harness ساخته شده و در GitHub در دسترس است. walkinglabs/learn-harness-engineering

Harness engineering is the new core AI skill. This repo teaches it for free. 14 lectures, 8 projects, 4 frontier harness breakdowns: Link to the repo: walkinglabs/%E2%80%A6 t.co

7 Viral AI Agent Repos: 4 Checks Before You Install One Seven popular AI agent repos, four checks before you install any of them (checked 20-21 Oct 2026; star counts change daily). 1. Who made it? Anthropic Cybersecurity Skills is an independent community project by @mukul975. Its README says "Not affiliated with Anthropic PBC". 2. Is it the right repo? Two separate curated lists are both called Awesome Harness Engineering (ai-boost and walkinglabs), and several repos use "Agent Memory"-style names. Match the GitHub owner, not just the name. 3. The licence. OpenViking is AGPL-3.0, which has conditions if you offer a modified version as a service. Browser Use, Scientific Agent Skills and Diagram Design are MIT; agentmemory and Anthropic Cybersecurity Skills are Apache-2.0. Read the licence before business use. 4. The real cost. Browser Use's code is MIT and free, but you pay for the AI model you connect to it. Its optional Browser Use Cloud starts from $0.02 per browser-hour (the project's own figure). Also: agentmemory's "95.2% retrieval" and Scientific Agent Skills' "250,000+ scientists" are the projects' own claims. Diagram Design has a Claude Code plugin and also works with other agents. Repos (all 7, public on GitHub): Browser Use: browser-use/browser-use agentmemory: rohitg00/agentmemory Scientific Agent Skills: K-Dense-AI/scientific-agent-skills Diagram Design: cathrynlavery/diagram-design Anthropic Cybersecurity Skills (community project, not made by Anthropic): mukul975/Anthropic-Cybersecurity-Skills Awesome Harness Engineering (two lists share the name): ai-boost/awesome-harness-engineering and walkinglabs/awesome-harness-engineering OpenViking (AGPL-3.0): volcengine/OpenViking Browser Use Cloud pricing: browser-use.com Which check would have caught you out? #AI #AIagents #GitHub #shorts Made with AI-generated visuals and voice.

Learn Harness Engineering for FREE 🚀 14 lectures + 8 hands-on projects covering: → Agent memory & context → Testing & verification → Multi-agent workflows → Reliable AI coding agents GitHub: walkinglabs/learning-harness-engineering t.co

Deux cours complets et gratuits sur Github que j'ai transformés en skills pour mon Claude Code, et que je conseille vivement à ceux qui construisent avec des agents et/ou qui veulent mieux comprendre à quoi ressemble le moteur : - AI Engineering from Scratch, de Rohit Ghumare ( rohitg00/ai-engineering-from-scratch, licence MIT ) : 523 leçons, de l'algèbre linéaire jusqu'aux agents en production, en naviguant entre le RAG, les evals, le MCP, le serving et la sécurité, avec du code à chaque leçon. - Learn Harness Engineering, de walkinglabs ( walkinglabs/learn-harness-engineering, MIT aussi ) : 14 cours et 8 projets sur le harness, c'est-à-dire tout ce qui entoure le modèle (les instructions, les outils, l'état entre deux sessions, les tests), avec en bonus le décorticage des harness de Claude Code, Codex, DeepSeek et Pi. Je ne les ai pas lus de A à Z, j'ai surtout demandé à Claude Code de cloner chaque repo et de le distiller en une skill, donc des fiches par thème plus un fichier qui dit quand aller les chercher, et maintenant, quand je bloque sur un problème agentique, je pose la question à mes coachs Claude qui me partagent la leçon à ouvrir et m'aident à le résoudre.