The workbench
Platform work and weekend experiments.
Some of this ships for thousands of developers. Some of it was a Saturday on a Mac. Both belong here.
In progress & shipping
Everything on the bench
Ordered by how actively I'm touching it. Open a card for the honest write-up, including the caveats.
- CLI · Agent readiness
Agentlint
Audit whether AI agents can find, understand, and use your website with Agentlint, a deterministic CLI scanner that backs its findings with evidence.
Active · @timbenniks/agentlint
- SDK · TypeScript
Contentstack Platform SDK
Build with one TypeScript SDK for Contentstack, covering the Content Management API, OAuth, webhooks, image transforms, and generative AI.
Active · @timbenniks/contentstack-platform-sdk
- OSS · Nuxt module
Nuxt Contentstack
The Nuxt module I wish Contentstack shipped: typed composables, live preview, visual builder, personalization, and image optimization in one install.
OSS · nuxt-contentstack on npm
- OSS · Models as code
Contentstack Stacksmith
Content types as TypeScript you can import, compile, diff, document, type-generate, and safely promote, so the UI is no longer the source of truth.
OSS · @timbenniks/contentstack-stacksmith
- OSS · WebMCP
Contentstack WebMCP
Expose published Contentstack content to browser agents through WebMCP, with framework-agnostic TypeScript tools and adapters for React and Next.js.
Experimental · @timbenniks/contentstack-webmcp
- MCP · Agent skills
Contentstack MCP Hub
A hub of Contentstack agent skills with role-based access control. Agents only reach permitted data, and product managers can propose new skills.
Active · Internal + open contributions
- macOS app · MCP
Open Loops
A local-first macOS tracker for work you hand to coding agents. SQLite on your machine, git-aware tasks, and a full backlog API over MCP.
Open source · macOS · MIT
- MCP · Local-first
Turbo Relay
A local-first intelligence layer for sanctioned AI agents. Agents write evidence-backed knowledge through MCP; humans review, approve, and promote it.
Open source · macOS · MCP
- TUI · Agent orchestration
Dex
Orchestrate AI engineering in the terminal with Dex, a local-first tool for tickets, worktrees, tests, pull requests, reviews, and human approval.
Active · local-first · Bun
- macOS app · Skills
Loadout
Manage Skills and MCP servers across Claude Code, Codex, and Cursor with Loadout, a native macOS app that shows what is installed and how tools differ.
Early · macOS 15 · Swift
- macOS app · Local-first
ButterKeys
A menu bar app that fixes the typos your hands already know how to make (teh, writign, int he) on the machine, with no account and no network.
macOS 14 · local-first
- OSS · Agent workflow
Cursor Rules
A reusable Cursor ruleset and command kit for SaaS projects, with planning, small diffs, root-cause debugging, accessibility, and checks before shipping.
Open source · MIT
- OSS · CLI
Contentstack OpenAPI Plugin
Generate OpenAPI 3.1 specs from a Contentstack stack with a csdx plugin covering Delivery and Management APIs, schemas, regions, and security.
OSS · @contentstack/cli-plugin-openapi
- Experiment
DoorBell DevRel
An experiment in AI-generated developer videos at scale, using minimal production code to explore adaptive content and the cost of creating more videos.
Live · doorbell-devrel.timbenniks.dev
- Workgroup
MACH Alliance Enterprise AI Agents
Co-chairing the workgroup that is trying to define how composable architecture and AI agents get adopted when the buyer has real governance, not a weekend demo.
Ongoing · MACH Tech Council
Want to collaborate, contribute, or drag a weekend experiment into production? Write me.