
Rhys
@RhysSullivan • 55,915 subscribers
building https://t.co/gIFOwRUrLU to connect any agent to every tool, API, and service your team uses
Shorts
Videos

- get a local code mode mcp gateway add all of your MCPs once, use them with any client
Rhys25,261 просмотров • 20 часов назад

I'm now building Executor full time as a startup! The state of tool calling is a mess: - Everyone is using different agents - You have no idea what actions are going to run - Destructive actions are treated the same as normal Executor lets you set up everything once & use it with any agent. You're able to control what tools can be called, require approval on destructive actions, and invite your team to all use them. Under the hood, it's built on codemode to let you add thousands of tools with 0 context bloat. I've been using it for a month so far and it has completely changed how I interact with agents. There's so much to be built here, immediately next up on the roadmap is workspaces, skills, workflows, and generative ui. Everything is being built open source over at there's a lot more coming on an SDK to embed it into your own agents, a self hostable cloud app, and plugins There's an early beta version over at It's very early on - if you hit any bugs let me know and I'll get them fixed up, excited to share more as I build it!
Rhys200,267 просмотров • 26 дней назад

My favorite videos are people showing ChatGPT a terrible scenario and it not caring at all
Rhys1,243,967 просмотров • 5 месяцев назад

MCP sucking is a harness problem, not an MCP problem MCP unlocks behavior that is fundamentally impossible to get via CLI or APIs Bad auth, too much context usage, all get solved with an execution layer - your agent writes code to progressively discover and call tools
Rhys375,725 просмотров • 2 месяцев назад

like it or not, this is what software engineering in 2026 will be +53,395 characters on a 100 line PR
Rhys458,649 просмотров • 5 месяцев назад

I'm concerned we're entering a local maxima with CLIs, they're the wrong interface for agents The right interface is regular REST APIs with CIMD (same spec that MCP uses to allow for dynamic client registration) Your agent then writes code to interact with the API (like Cloudflare codemode) Think about how this works for humans today for the following action: "I want to set a DNS record on my domain" -> You Google "Vercel set DNS records" -> Docs page tells you what buttons to press -> You press buttons on a website, those call an API Now for agents, they search Google: -> "Set DNS record on Vercel Domain" -> they land on the same docs page, except it outlines what api endpoints are used as well -> the agent then calls those api endpoints for you, credentials are dynamically inserted where the agent can run them -> (optional) set auto approval policies / require approval of all non GET options by default You don't need separate interfaces for agents, nor do you really need separate skills for them CLIs have terrible discoverability, no input / output typing, they're harder to make profiles for for allowed / disallowed tools They work as a stop gap solution, but companies should be focusing on making good docs and APIs, not CLIs I've been prototyping this over at (open source if you want to play with what this world would look like - still early on it so appreciate feedback - open source and can run completely on your machine
Rhys220,825 просмотров • 3 месяцев назад

executor now has a desktop app! add whatever MCPs / OpenAPIs / GraphQL servers you want once and then every agent can use them converts them all into code mode under the hood, so you can have thousands of tools and no context bloat everything stays 100% local on your device
Rhys44,248 просмотров • 22 дней назад

this is one of the most common problems on react sites, but it's solvable with less than 10 lines of javascript you can see how what i type gets wiped out after hydration, but if you use an inline script tag like shown in this demo your input seamlessly transitions
Rhys178,655 просмотров • 4 месяцев назад

i hate the way tool calling works today, so i built a fix for it its called `executor` and it lets your agent run code to call any API / MCP / GraphQL server rather than installing CLIs this is a soft launch, you can try it with npm i -g executor but im still making it great
Rhys128,873 просмотров • 2 месяцев назад

you can use the browser in cursor to watch tiktok while your agents work!
Rhys152,828 просмотров • 3 месяцев назад

Are you guys aware they’re making Mark Zuckerberg edits on TikTok
Rhys261,184 просмотров • 9 месяцев назад

One approach for requiring approval of destructive actions is giving the user a URL to approve it at In this, the returned result of the execute tool tells the model to: - Give the user a URL to approve the action - Immediately call `resume` which waits on the approval
Rhys18,768 просмотров • 17 дней назад

playwriter is exactly what i have been looking for in giving Claude access to a browser nice work Tommy D. Rossi
Rhys109,967 просмотров • 5 месяцев назад