Announcing Open Knowledge Compiler: a compiler for the Open Knowledge Format

Converting Documents to Markdown With MarkItDown Quiz

Check your MarkItDown skills. Convert documents to LLM-ready Markdown, use the MCP server, and get image descriptions. Try the quiz.

How to Use Claude Code Skills for Better Python Docstrings Quiz

Check your understanding of Claude Code skills, from SKILL.md frontmatter and reference files to bundled scripts and personal skills.

The Missing Cent: A Beginner’s Guide to Harness Engineering.

The Missing Cent: A Beginner’s Guide to Harness Engineering. AI agents can write code, but can you trust it? Part 1 of my Harness Engineering From Scratch series. This is Part 1 of my series …

Secure Your AI Agents – Free Model Context Protocol (MCP) Security Course

The Model Context Protocol (MCP) helps connect LLMs to external tools, databases, and APIs. But giving AI agents hands and feet to take real-world actions introduces an entirely new attack surface. We

10 Best AI GitHub Repositories to Supercharge Your Agent

GitHub là kho lớn nhất chứa công cụ AI miễn phí nhưng phần lớn lập trình viên chưa khai thác hiệu quả. Các agent như Claude Code thường được cài đặt mà không tận dụng được nguồn tài nguyên phong phú trên GitHub. Các kho lưu trữ AI hàng đầu như LangChain, LlamaIndex hay AutoGPT cung cấp framework mạnh để xây dựng agent thông minh hơn. Việc kết hợp các công cụ này có thể tăng đáng kể khả năng xử lý và tự động hóa của ứng dụng AI.

Bài viết này giúp bạn khám phá 10 kho GitHub AI mạnh nhất để tối ưu hóa khả năng của trợ lý lập trình.

Vercel MCP now supports Client ID Metadata Documents

Vercel MCP now accepts Client ID Metadata Documents (CIMD) as OAuth client IDs, so MCP clients connect without pre-registration or allowlisting.

Agentic Pipelines is generally available: run agents in Cloud or on your own Linux runners

Bitbucket's Agentic Pipelines is now generally available on all paid Cloud plans. Agents can run on Atlassian's cloud runners or on self-hosted Linux Docker (x86_64 and arm64) runners. Teams can now bring their own AI model, with Claude and Codex supported alongside Rovo Dev. Four built-in system agents handle flaky tests, failed steps, test optimization and cleanup, and native Atlassian Rovo MCP integration gives agents access to Jira, Confluence and Bitbucket context. Atlassian reports a 95% first-run merge rate on automated vulnerability fixes and one team saving 1.5 developer-days per week on documentation updates.

Why Agents Are Soon Only Going to Have 1 Tool

Instead of triggering tools one at a time across turns, agents are collapsing their tool catalog into a single exec(code) tool—chaining, filtering, and awaiting actions inside an isolated sandbox.