Executor is joining the YC S26 batch! We're building an open source MCP gateway to connect any agent to any service Your team is constantly spinning up new agents, trying out new tools, wrangling multiple accounts. You need one place to configure everything once, and use them anywhere. Executor gives you the ability to connect your agents to thousands of tools in a way that keeps you in control. Giving agents access to production services and data should be easy and predictable Since launching the beta we've: - Shipped a self-hostable Docker version - Shipped a desktop app - Shipped setup by chatting with your agent - Shipped multi-account support - Hit 2,000 GitHub stars - Built a product loved by thousands of users Truly appreciate all of the early support on it, has been incredible seeing all the ways people use it There's so much to build here. The past month has been laying the foundation. Now that that's in place, next up is custom tools, generative UI, and workflows. Setting it up is as easy as asking your agent "help use executor.sh". Incredibly excited about what's next, let me know all your feedback!

anyone interested in taking over my Answer Overflow project (web indexing of discord servers)? ~1m visitors / month from Google, ~500 Discord servers use it I don't have much time to maintain it these days but it still provides value to some people, may fit well a company

rough thoughts but it seems like most tool calls should be async openai did this with their ask questions tool, but why not do it for every tool in the harness? give the model the ability to make any invocation not awaited

lets see if this works

Here's Rhys' practical guide to shipping an MCP your users want: - Your MCP should be able to do everything your dashboard can Yes including things like deleting resources. The way to make this practical inside of an agent while not having things be unsafe is to deep link them into your product from inside the MCP - Do not ship lazy loading / codemode inside of your MCP CodeMode is a harness detail. Most harnesses (Claude / Codex / OpenCode) support codemode now, the problem is if you have two codemode MCPs they don't compose nicely (Executor v2 will still support CodeMode, but, will start to default to a transparent tool proxy for better clients) - Ship a search docs / skills tool Agents love these and it helps give them more understanding of your product MCP is getting skills over mcp which will help here in the future - Have a deep link into product tool Let the agent generate a URL that brings them into your product, people still want to use your dashboard and data visualization! They just don't want to click through things - Customization I think this matters less over time, but, you can allow people to select 'toolsets' of things to connect with to clients. Some clients don't support customizing tool selections and then it's also nice to have tool permissions set to the auth token - Let people OAuth from whatever client they want Please stop putting restrictions on which clients can authenticate to MCP servers, your users hate it, it doesn't improve security, all it does is add more friction PostHog and Sentry are my two 'AI native' companies to look at today, they both have an excellent onboarding, MCP / CLI experience, if you need a place to learn from look at them To be honest though, while all the above is helpful just shipping your API spec + CIMD OAuth to it is enough for 99% of agents to have a good experience

opening your agents.md after a month of not looking at it

ai adoption is going well

OpenAI’s only possible response to Muse is that they need to buy Tamagotchi

The Zuck basically spent 15 years fighting for his company to stay alive due to lack of owning the platform, while Apple got lazy off of 30% fees None of the competitors, Apple / Google, are gonna have the hunger he does to win

Executor will be getting Muse support as soon as possible 🫡

he was right

there's a development flag in codex called: mcp_oauth_refresh_coordination you can enable it and i believe it'll fix the common MCP auth problem codex users face it's a development flag so yadadaya use at your own risk / ask your agent about it

everyone else please take notes on what i want you bus ads to look like

my favorite early form of agent <-> agent communication is watching my agent chat with the support agents on websites

how are there 100 speech to text companies that have raised a collective 10 billion in funding and speech to text still sucks

Super excited to cohost this hackathon with a bunch of amazing companies Executor SDK will be live by then so if you're there you'll be able to build personal agents that can do anything Register here! luma.com/build-agents?tk=PAZ…

It's hack time! Join and build your own personal agent! Full day hackathon hosted by the agent stack w/ food trucks, credits for hackers, six-figure prizes, after-party, and of course, plenty of time to hack 🤖 Join @neondatabase, @mastra, @ExaAILabs, @usekernel, @assistantui, @executorsh, @flydotio, and @agentmail for Build Personal Agents Hack! luma.com/build-agents