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 https://t.co/gIFOwRUrLU". Incredibly excited about what's next, let me know all your feedback!
not quite sure what the good implementation looks like here, but, you can:
- either jump onto the bun -e / node -e execution format in some way (but then you don't jump onto perl / python etc)
- expose a .spawn tool in your codemode executor (ugly imo, and then you're still just using a subset)
- make the mcp calls callable over cli via something like `opencode mcp list` `opencode mcp call`, it's not as nice though and i don't see how that'd work with sessions, although in the bash command you could maybe set a like OPENCODE_MCP_SESSION env var it reads from in the spawn call
the main issue i have is that we're shipping interpreters / sandbox runtimes to users who are already running in dangerously skip permissions, it should be able to use whatever code execution they have on their computer already
after using it in most harnesses, i think the sandboxing of codemode was ultimately a mistake?
if users are already running with auto / dangerously skip permissions, by sandboxing the codemode it doesn't compose as nicely with bash
@_christinacodes yeah but you can build micro uis ontop of clis, you can't build micro uis ontop of dashboards
chat is such a better ux over hunting through dashboards trying to do things