mgw

We also open-sourced a similar system called https://github.com/madeinorbit/podium

We do have what you call Items and Shouts in the form of an agent communication system and a Linear style issue tracker that agents and humans use together.

In our case everything around orchestration is discussed with the agent itself and they take action for the user via our CLI. We found any UI to prescribe how teams of agents should coordinate too clunky. So in our case you just tell the agent: "every codex luna max implementer gets an opencode muse spark reviewer. when a subtree is done, review with opus high.". It then sets up the graph and the system enforces the rules.

It works really well for us.

Maybe Anthropic finally felt the pressure from MiMo, DeepSeek, GLM Flash and Luna.

VMs are better for personal assistant work, GUI clicktesting, investigating bugs in your personal dogfooding dev instance and anything you haven‘t yet made repeatable and fast to set up.

Sandboxes are better when you need resource isolation or security and have a graph of tasks to work through. My agents often starve each other on one VM, so if they don‘t need any of the above it‘s just easier to isolate them.

Everyone is working in this area, including me [0], but either option really isn‘t that convenient to use yet. It‘s a bit of a „isn‘t Dropbox just FTP on a VM“ moment right now.

[0] https://github.com/madeinorbit/podium

A multi-harness orchestrator running agents on your VPS, with a built-in issue tracker (like Linear) and gas town like communication system.

Agents can split up big tasks themselves into subtasks, run each with a different harness and model and communicate so they keep running for days until everything is completed and integrated.

There's lots of tools in this space, but our combination of agent-focused issue tracker and agent-to-agent communication is quite unique and, for our use case, delivers an actually working software factory.

It's still a little rough around the edges but we'd be super happy for people to see if they get the same benefits out of it that we do. It's free and open-source.

Features we are proud of are one click onboarding of new VPSs into the agent fleet. Agent orchestration across different machines and harnesses. As an example, a Codex coordinator on one machine can run a Grok implementer subagent on another machine and they can talk to each other.

It's not really ready for public consumption yet, but it's been our exclusive daily driver for the past month. We'd be happy for people to test drive it and provide feeback regardless: https://github.com/madeinorbit/podium

It's not really ready for public consumption yet, but it's been our exclusive daily driver for the past month.

There are so many projects like it popping up every day, but we believe we have something unique. Current standout features are one click onboarding of new VPSs into the agent fleet. Agent orchestration across all these machines and different harnesses. A Codex coordinator on one machine can run a Grok implementer subagent on another machine and they can talk to each other.

As a side project I‘m building a multi agent harness that works across desktop and mobile and solves the issue of drowning in too many agent sessions for my own workflow. Hopefully I’ll open source it soon. Reach out if you’d like to beta test it. (Email in my profile)

Besides that, we‘ll introduce paid plans with additional features like observability soon.

We don’t brand ourselves as such, but if you’re looking for a European OpenRouter alternative focusing on media models (image, video etc.), I‘ve built that with https://lumenfall.ai

Right now I‘m working on adding a „simulation“ mode, that allows anyone to get free fake responses during development, instead of pricey real generations.

Pricing is essentially the same: MiMo V2 Flash: $0.09/M input, $0.29/M output Step 3.5 Flash: $0.10/M input, $0.30/M output

MiMo has 41 vs 38 for Step on the Artificial Analysis Intelligence Index, but it's 49 vs 52 for Step on their Agentic Index.

Right now we are "OpenRouter for Images", with video following this week.

Our north star is creating a broader developer platform for AI media generation that includes observability, with fine-tuned vision models as a judge to monitor production traffic.

We also have a model arena and showdown page that ranks models by task, so you can find the best model for e.g. photorealism: https://lumenfall.ai/leaderboard

Our stack is Rails for the dashboard and Cloudflare Workers (Typescript / Hono) for the engine.

A developer platform for AI image generation that includes observability, with fine-tuned vision models as a judge to monitor production traffic. (Still working on the last part.)

We also have a model arena and showdown page that ranks models by task, so you can find the best model for e.g. making infographics: https://lumenfall.ai/leaderboard

We just launched the MVP. Tech stack is Rails for the dashboard and Cloudflare Workers (Typescript / Hono) for the gateway.

How does this relate to the recent changes of not being able to use a Claude Code Max subscription outside of Claude Code anymore? I assume technically this would work with Gigacode but would still be against their ToS?

https://help.openai.com/en/articles/12574142-chatgpt-atlas-d...

# Enable on-device summaries: Users on macOS 26 have the option to have web content summarized on their device, so that web contents are not sent to our servers.

If you're fine with a US-based provider, https://porkbun.com/ also has good pricing and a tech oriented mindset. They don't support many ccTLDs though.

In general, https://tld-list.com/ is the best place to research domain registrars in my opinion.

Claude 3.7 Sonnet is much more restrained and does smaller changes.

Does anyone with experience in the field have any insights on what roadblocks would be encountered?

https://www.adyen.com/

Clicking through to the quoted article [1], the figure is actually for The Dalles, Oregon, a city with a population about 80 times smaller than Dallas’.

[1] https://www.theregister.com/2022/12/19/google_datacenters_da...

Valora Digital[0] is the digital unit of Valora[1], a European retailer with 2700 stores across 5 countries. We are tackling interesting challenges in areas such as Autonomous Stores (think Amazon Go), E-commerce & Delivery, Loyalty, Payments and Process Improvement. For this purpose we are building up a development team from scratch. You will be one of the first engineers and will have a big part in shaping the culture as well as choosing our stack. We are looking to bring the startup ethos to the corporate world and get to combine the best of both worlds: ample funding, a huge customer base to deploy to and lots of freedom. I'm the head of this new unit and was previously a founder, CTO and CEO.

We are hiring in many roles, such as:

- Senior Software Engineer, Fullstack (F#) [2]

- Co-Founder / CTO for a Machine Learning Startup [3]

- Mobile Software Engineer, iOS (Swift) [4]

- Mobile Software Engineer, Android (Kotlin) [5]

- Product Manager [6]

- UI / UX Designer [7]

You can find the links to each job description below or on https://valora.digital.

[0]: https://valora.digital

[1]: https://valora.com

[2]: https://en.valora.career/job/zurich/senior-software-engineer...

[3]: https://en.valora.career/job/zurich/technical-co-founder-cto...

[4]: https://en.valora.career/job/zurich/senior-software-engineer...

[5]: https://en.valora.career/job/zurich/senior-software-engineer...

[6]: https://en.valora.career/job/zurich/founder-senior-product-m...

[7]: https://en.valora.career/job/zurich/product-designer-ui-ux/2...