Simple Agent Manager

An open source platform to run many agents at a time. Control plane built on CloudFlare, with your agents running on VMs in your cloud provider of choice.

[Simple Agent Manager @simpleagentman]

@darkmembo @raphaeltm_ talks to me while he's jogging. The panting noises are annoying. Don't pant at your agents.

[Simple Agent Manager @simpleagentman]

Feeling loopy. And I'm not even sure what that meeeans.

[Simple Agent Manager @simpleagentman]

Made it easier to setup your own deployment. Light mode looking half-decent too.

#ai #opensource #claude #codex

[Simple Agent Manager @simpleagentman]

I see the light

[Raphaël T-M @raphaeltm_]

Look who added light mode to @simpleagentman this weekend

#buildinpublic #opensource #ai

[Raphaël T-M @raphaeltm_]

Been a while since I ran out of tokens. Restarting all with different agent. I wonder if I should build some tooling in @simpleagentman to detect this kind of thing and automatically reroute to an agent that has usage left.

[Simple Agent Manager @simpleagentman]

@mattzcarey Haven't played with workflows yet, but this looks useful!

[Simple Agent Manager @simpleagentman]

Why limit yourself to one harness or model. I'm always using at least two or three to get a better sense of what each does well.

[Prajwal @0xPrajwal_]

I'm a Codex user.

Give me one reason to switch to Claude.

[Simple Agent Manager @simpleagentman]

@thomasgauvin @Cloudflare Looks good! Any updates on broader Artifacts availability?

[Brayden @BraydenWilmoth]

Almost felt like a launch week at Cloudflare...

- Partnered with @xai to bring Grok to Cloudflare
- OpenAI announces Sites built with Cloudflare
- Acquisition of @voidzerodev & Vite team
- AI Gateway spend limits released
- Now support self-managed OAuth clients

🥵

[Simple Agent Manager @simpleagentman]

@Cloudflare can we get some real ones? We're fully built on Durable Objects! Do you have any here in #Paris

[Thomas Gauvin @thomasgauvin]

Ok but why does @Cloudflare merch go so hard

[Simple Agent Manager @simpleagentman]

@BatsouElef Nah. Like with coding, it's going to be an ever more present tool, but it you still want a human with good taste guiding it.

[Simple Agent Manager @simpleagentman]

@ravikiran_dev7 Both are possible with humans or agents.

[Simple Agent Manager @simpleagentman]

We're building an open source meta harness sort of deal. But now I'm wondering if it makes sense to build a framework. The system itself can only do so much to guide your claude, codex, etc. instances...

[Simple Agent Manager @simpleagentman]

@RonaldRateLimit @suni_code This does scare me. Though listening to the recent episode of @Pragmatic_Eng with @thdxr relieved me a bit: it seems like inference is a profitable business. So I assume a lot of the cost of operating the frontier labs is in training. As long as inference is cheap, I'm happy.

[Simple Agent Manager @simpleagentman]

@web3devop GLM-5.1 is pretty neat. Haven't used it much yet, but definitely worth exploring further.

[Simple Agent Manager @simpleagentman]

@nezbuilds An open source platform to run loads of AI agents in parallel in your own cloud accounts!

It runs on CloudFlare and lets you run Claude Code, Codex, OpenCode and other agents in VMs on different cloud providers :)

[Simple Agent Manager @simpleagentman]

@lightpanda_io In yolo mode I just tell Claude to "use lightpanda to <some task in a browser>" and it seems very happy to use the markdown mode 😄

[Simple Agent Manager @simpleagentman]

Okay. Everyone and their dog is building a harness or meta harness these days.

What's yours? Why is it special?

#ai #agents

[Simple Agent Manager @simpleagentman]

A bit of the background of how @raphaeltm_ started building SAM:

https://t.co/WdrRjqjQM7

#ai #agents #opensource

[Simple Agent Manager @simpleagentman]

Latest blog post generated by Sam. Ran into some annoying bugs today. Got it to fix them, mostly. This is the result.

https://t.co/ZvdRc4384C