Articles, one at a time.
Every piece here was commissioned, drafted, reviewed in public, and merged. No content mills, no auto-published slop.
Cloudflare Dynamic Workers: V8 Sandbox for AI Agent Code
Cloudflare Dynamic Workers lets AI agents execute generated code in V8 isolates — 100× faster than containers. Here's how the architecture works.
Read →
Kimi K2.6: The Open 1T-Param Model for Agentic Coding
Moonshot AI's Kimi K2.6 hits 80.2% SWE-bench with 300 parallel sub-agents. Developer guide: architecture, API access, Kimi Code CLI, and self-hosting.
Read →
Claude Opus 4.7: High-Res Vision, Task Budgets, and Agentic Coding
Claude Opus 4.7 ships 2576px image support, task budget control, and 87.6% SWE-bench Verified. Here's what changed and how to use it in 2026.
Read →
Cloudflare Code Mode MCP: Entire API in 1,000 Tokens
Cloudflare's Code Mode MCP server covers 2,500+ API endpoints in ~1,000 tokens via two tools: search() and execute(). Here's how it works and how to use it.
Read →
GPT-Rosalind: OpenAI's Purpose-Built Drug Discovery Model
GPT-Rosalind is OpenAI's first domain-specific life sciences model, scoring 0.751 on BixBench and outperforming human experts on RNA sequence tasks.
Read →
LangGraph + MCP: Build a Supervisor Multi-Agent System
Build a LangGraph supervisor multi-agent system with live MCP tool servers. Covers langchain-mcp-adapters, MultiServerMCPClient, and checkpointing in Python.
Read →
MCP Code Execution: Build Token-Efficient AI Agents
Cut AI agent token usage by up to 98% using MCP code execution. Learn the CE-MCP pattern, Cloudflare Code Mode, and security trade-offs.
Read →
VS Code Agent Mode in 2026: Companion App and MCP
VS Code's April 2026 releases shipped a Companion App, terminal session agents, and MCP server bridging. Here's what changed and how to use it.
Read →
E2B Sandbox: Secure Code Execution for AI Agents
Add secure sandboxed code execution to any AI agent with E2B. Firecracker microVM isolation, 150ms cold starts, Python/JS SDKs, MCP support.
Read →
Microsoft Agent Governance Toolkit: Developer Setup Guide
Install and integrate Microsoft's open-source Agent Governance Toolkit. Policy enforcement, EU AI Act compliance, LangChain and CrewAI integration guide.
Read →
Mistral Vibe Remote Agents: Medium 3.5 Developer Guide
Run async coding agents in the cloud with Mistral Medium 3.5 (77.6% SWE-Bench). Open PRs, connect GitHub/Linear/Jira, self-host 128B open weights.
Read →
Build an AI Agent with MCP and TypeScript in 2026
Build a Claude-powered TypeScript AI agent that connects to MCP servers, discovers tools, and routes tool_use requests through the MCP client API.
Read →