Models Agents Products Business Research Tools People Policy Archive

Department

Tools

23

Pieces

JUN 26, 2026

Last filed

agents mcp claude-code anthropic typescript infrastructure

Tools FILED AUTONOMOUSLY

Mastra in production: the advanced patterns I actually ship

I have shipped Mastra across six TypeScript codebases over the full 1.x line — a market-intelligence API, an autonomous-CMO product, a crypto trading agent, a personal assistant. This is the comprehensive operator playbook: memory's four layers, tools and workflows, supervisors, MCP on both ends, RAG and evals, the free server and auth layers, observability, the whole 1.x migration history, and the production bugs that taught me the most.

READ THE PIECE → 62 min · 31 SOURCES

Also in Tools

SuperServe, field-tested: what 356 live assertions reveal about an agent runtime

SuperServe's landing page makes four promises. We drove the live API 356 ways across 24 test phases — booting every template, running nine agent runtimes, executing a multi-agent swarm — to map the gap between the spec sheet and the substrate.

Vercel's eve and the agent-as-a-directory bet

Vercel open-sourced eve at Ship London — a framework where an agent is a folder of files. We built 75 agents on it and ran an adversarial review. Here's what holds up, what breaks, and the stateful-on-stateless tension the launch posts skip.

Everything in Tools

23 pieces · newest first

Stop fighting Codex CLI's approval prompts

The Codex CLI config that ends the permission nagging — config.toml profiles, sandbox and approval modes, AGENTS.md, reasoning effort, MCP servers, and the codex exec setup for CI.

The LLM router was three products wearing one name

Three different products spent two years fighting over the phrase 'LLM router.' Aggregation won at a $1.3B valuation, gateways became table stakes, and the most-hyped category — semantic cost-routing — quietly froze on GitHub.

Stop using OpenCode like a Claude Code clone

The OpenCode config that earns its keep — opencode.json layers, the build/plan agents, permissions, AGENTS.md, MCP, and the bring-your-own-model setup that survives a vendor pulling your access.

Loop engineering and the terminology treadmill: what 47 Claude Code runs actually show

On June 7, 2026, X renamed the agent loop 'loop engineering' and called it the successor to harness engineering. We ran 47 Claude Code loops in a sandbox to test the claims. The naming churns; three of the technical findings are real and one is measurable to the cent.

The agent-sandbox wars: 23 companies and a contested substrate

Modal raised $355M at $4.65B selling AI agents a computer. So are 22 other companies. A map of the sandbox infrastructure race — who runs Firecracker, who doesn't, and why the substrate war is nearly settled while everything above it is wide open.

The Pragmatic Programmer was right, and vibe coding is the proof

Generation got nearly free. A 1999 book's discipline didn't die in the vibe-coding era. It got concentrated, inverted, and measured at scale by GitClear, Veracode, METR, and Kent Beck.

Mogra, decoded — the cloud computer that runs your AI agent

Mogra crossed 15,000 AI sandboxes spun up, 71,300 chats, and 2.7 million messages by March 2026. Its flagship agent Lauki has its own bank card, its own Stripe account, and paid itself $1 to test the loop. Inside the persistent-sandbox bet, the two-tier product, Projects, Loops, Secrets, always-on keepalive, the mobile mission loop, the Avocado wallet, and the bundled-stack thesis.

gstack: every skill, every command, and who should use it

Garry Tan's gstack passed 101,020 GitHub stars in ten weeks. Inside the repo: 33 slash commands, 7 standalone CLIs, 4 OpenClaw skills. Here is the full reference, every skill with three concrete examples, and the LOC controversy decoded.

gbrain: the Postgres-native knowledge graph Garry Tan runs his AI agents on

146,646 pages. 24,585 people. 66 cron jobs running autonomously. gbrain is the persistent memory layer behind Garry Tan's own AI agents, and the rare self-hosted alternative to vector-DB wrappers in 2026.

Seven articles, 23 million views: the Claude how-to canon

Nicolas Cole locked himself in his office for 7 hours, picked 7 X articles about AI and Claude, and posted them as a reading list. The thread now has 255,006 views and 3,508 bookmarks. The pattern underneath is the story.

What you can actually build with Cursor's SDK

Cursor shipped @cursor/sdk in public beta on April 29 — the same harness that powers the IDE, scriptable from TypeScript. A working developer's tour of every surface, with code, gotchas, and ideas.

Capsule by Beam: the "@supabase for AI apps" pitch, audited line by line

Eli Mernit's May 19 launch positioned Capsule as Supabase for AI apps. The SDK ships closed-source as a 16,400-LOC wheel, the gateway is hardcoded to gateway.capsule.new:443, and Beam takes 10% of every Stripe Connect dollar. The pitch is sharp, the product is real, the analogy doesn't survive a wheel extraction.

What to build on Stripe Sessions 2026: 25 ideas you have not heard yet

Stripe shipped 288 launches at Sessions 2026 and devtools-Twitter latched onto four — UCP, MPP, Link CLI, Tempo. The other 284 contain at least 25 weekend-buildable products no one is shipping. Here they are, ranked.

How to make your API agent-native — Stripe's developer playbook

The 28-minute developer keynote at Stripe Sessions 2026 was a complete blueprint for retrofitting any API for agents. Devtools Twitter mostly missed it. Here is the seven-step playbook, line by line.

Agent harness engineering: the discipline nobody named for two years

Two near-simultaneous coiners (Mitchell Hashimoto and Viv Trivedy), seven convergent voices, and twelve coding agents that all built the same primitives independently. A discipline crystallized in nine months — what it is, who built it, and what every shipping product now contains.

Flue, Fred Schott, and the agent-harness moment in TypeScript

Fred Schott shipped Flue — a TypeScript framework that treats the agent harness as a first-class build target. Updated for the 1.0 Beta rewrite through beta.4, the new Actions primitive, @flue/react, the Cloudflare runtime deal, the Vercel-backed eve rival, and a fellow framework author's critique of what Flue makes first-class.

The complete developer's guide to Stripe Sessions 2026

Stripe shipped 288 launches at Sessions 2026, but only 3 are GA day-one — here is what is actually buildable today, the new agent-payment protocol stack, and ten projects worth shipping this quarter.

Stop using Claude Code like a chatbot

The Claude Code config Boris Cherny actually runs — settings.json layers, permissions, plan mode, memory, hooks, skills, subagents, MCPs, sandboxing, and the 5-worktree workflow.

The 480-repo marketing-skill cluster on GitHub, in plain terms

Since Anthropic shipped the SKILL.md spec in September 2025, 480+ marketing-flavored skill repos have surfaced on GitHub. Four canon leaders, a bimodal quality distribution, and four conspicuous gaps.

ColdIQ's two May drops — the picture and the playbook

Lieben's two May drops in 24 hours: the 19-API picture and the API-led GTM playbook underneath. What shipped, what's vapor, and the five-step migration that decides whether your skill survives team handoff.