building executor.sh to connect any agent to every tool, API, and service your team uses
Joined November 2007
- Tweets 12,069
- Following 1,345
- Followers 56,473
- Likes 28,357
2,724 Photos and videos
Pinned Tweet
May 8
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 github.com/RhysSullivan/exec…, 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 executor.sh. 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!
150
77
1,508
212,861
NYC gets the Knicks winning and we get Fable being taken away from us
unfair
nyc is partying, meanwhile sf is creating shareholder value.
3
19
2,513
it's starting
Jun 13
does anyone have the @ of that guy who could run chatgpt in his head and get the right answer? does he do fable 5?
9
53
2,056
50,718
11h
which of the AI PR review bots do people actually use and are good?
79
72
24,258
14h
true believers already gave anthropic their passport and drivers license to get fable access
So when do I give Anthropic my passport and retina scan and signed affidavit saying I will not let my chinese nationalist gf touch the keyboard when interacting with fable
8
8
234
15,221
14h
once europe checks twitter on monday they're gonna jump into action building competitive models
32
5
303
12,687
15h
this isn't inference advice but it'd put the probability we get a reset when fable comes back at about 90%
8
1
169
10,348
Jun 12
finding out fable spawned 100 fable subagents makes me feel like one of those parents who found out their kid spent thousands on microtransactions
29
31
2,179
54,369
Jun 13
I would love to be looking at maxed out usage limits right now
I didn’t know what I had
2
95
4,349
Jun 13
trying out some alternatives with fable access gone
你好，我的中国同志们！
133
9
916
80,419
Jun 12
one way to think on loops is that your agent should bring context to you, rather than you bringing context to your agent
7
1
106
7,975
Jun 12
A stupidly high leverage move for companies right now is to vibe code a test environment for people to use anonymously with your product
Throw it on Cloudflare w/ Durable Objects for state, enable people to use your product in their flows realistically with no API keys set
10
6
286
23,152
Jun 12
they should use a more secure package manager like npm
‼️ UPDATE: It just doesn't stop: Almost 900 Arch Linux packages infected now.
lists.archlinux.org/archives…
1
83
9,660
Jun 12
has anyone tried fable on different reasoning levels? i've mainly stuck to high, wondering if its worth giving a shot on low
24
68
21,629