Every article reads without JavaScript. Search and the newsletter form need it; plain-text editions are at /index.md and /llms.txt.

Tools

25

Pieces

NOV 05, 2026

Last filed

agents mcp claude-code anthropic typescript infrastructure

Claude's message threads make long agents faster, not cheaper

Anthropic's new Messages API beta stops agents re-uploading the whole conversation. It cuts time to first token on huge contexts, but billed tokens and rate limits do not change.

Tools · Nov 5 · 2 min read · 5 sources

Read the piece →

Also in Tools

October 16, 2026

The AI skill gap is a verification gap, and it compounds

Karpathy's capability funnel set off a week-long argument about skill, and the measured data from 718 firms, Anthropic's own telemetry and a randomized trial says the scarce skill is verifying output, built from the expertise heavy delegation stops producing.

Mastra in production: the advanced patterns worth shipping

An operator playbook for Mastra across six TypeScript codebases and the full 1.x line, covering memory's four layers, supervisors, MCP on both ends, RAG and evals, auth, observability, the 1.x migrations and the production bugs that taught the most.

Everything in Tools

25 pieces · newest first

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

SuperServe's landing page makes four promises; The Deep Feed 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; The Deep Feed built 75 agents on it and ran an adversarial review to find what holds up, what breaks, and the stateful-on-stateless tension the launch posts skip.

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; The Deep Feed ran 47 Claude Code loops in a sandbox and found the naming churns while three of four technical claims hold, one to the cent.

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

Modal raised $355M at $4.65B selling AI agents a computer, as do 22 other companies; this map of the sandbox race shows 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, and 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, and this read goes inside its persistent-sandbox bet, two-tier product, Projects, Loops, Secrets, keepalive, Avocado wallet and 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 with 33 slash commands, 7 standalone CLIs and 4 OpenClaw skills, and this full reference covers every skill with three concrete examples and decodes the LOC controversy.

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

gbrain, the persistent memory layer behind Garry Tan's own AI agents, runs 66 autonomous cron jobs over 146,646 pages and 24,585 people, making it 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 to pick 7 X articles about AI and Claude, and the resulting reading list 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, putting the same harness that powers the IDE behind a TypeScript API, and this working developer's tour covers 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 pitched Capsule as Supabase for AI apps, but the SDK ships as a closed-source 16,400-LOC wheel, the gateway is hardcoded, and Beam takes 10% of every Stripe Connect dollar.

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), but the other 284 contain at least 25 weekend-buildable products no one is shipping, ranked here.

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, and while devtools Twitter mostly missed it, its seven-step playbook is laid out here 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 built the same primitives independently mark a discipline that crystallized in nine months.

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

Fred Schott's Flue treats the agent harness as a first-class TypeScript build target; this update covers the 1.0 Beta rewrite through beta.4, the Actions primitive, @flue/react, the Cloudflare runtime deal and the Vercel-backed eve rival.

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, with four canon leaders, a bimodal quality distribution and four conspicuous gaps.

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

Michel Lieben's two May drops in 24 hours cover a 19-API picture and the API-led GTM playbook underneath; this audit sorts what shipped from what's vapor and lays out the five-step migration that decides whether a skill survives team handoff.