HN user

playcache

278 karma
Posts6
Comments107
View on HN

Should anyone be interested I am working on AgentUp:

https://github.com/RedDotRocket/AgentUp

I believe its quite unique as far as agents go. Runtime is config driven, so you can get caching, state management, security (oauth2, jwt) , Tools and MCP capabilities are granted based on scope allocation (file:read, api:write, map:generate) etc, retry handlers, push notifications / webhooks (for long running tasks). This means you can get a fully baked agent built in minutes, using just the CLI.

From there, when you need to customize and write you own business logic, you can code whatever you want and inherit all of AgentUps middleware, and have it as a plugin to the core. This is pretty neat, as it means you're plugins can be pinned as dependencies.

Plugin Example: https://github.com/RedDotRocket/AgentUp-systools

You then end up with a portable agent, where anyone can clone the repo, `agentup run` and like docker, it pulls in all it needs and is serving.

Its currently aligned with the A2A specification, so it will talk to Pydantic, Langchain and Google Agent SDK developed agents.

Its early days, but getting traction.

Previous to this , I created sigstore and have been building OpenSource for many years.

The docs also give a good overview: https://docs.agentup.dev

Hey,

I am Luke, an open source developer. I originally worked a lot in security (I created a software supply chain project called sigstore). Over the past couple of months, I spent some time building AI agents alongside chatting with other developers attempting the same , and there seemed to be a fair amount of fog in the air around how to do auth, middleware, and all the normal trappings.

AgentUp came out of that. I started to make the agents I was building into reproducible things, so I could then easily spin up other agents. From there I started to add more and it became a framework eventually.

I also noticed a lot of folks were building their own Tools / Function calls over and over, and i thought, it would be nice if these were pluggable, which is where the AgentUp plugin system came from.

So there is what I have started calling 'Core' agentUp, and then plugins (tools) are entry points with their own dedicated interfaces, yet they can inherit all of the cores middleware. Plugins are also limited by scopes, so the core can enforce fine grained access control to each plugin, using the familiar style of domain:type:capability (e.g system:admin: ["system:write", "system:read"]), this way systems can scope policy within token scopes (jwt, oauth2) and AgentUp will enforce for each user. I am yet to really dig into the isolation capabilities in python, but will try to spend some more time there if the project gets momentum.

Last but not least, the Agents are A2A compatible. JSON RPC, streaming / non streaming, Tasks, Parts, Artifacts etc. MCP servers exposed via the Agents are streamable HTTP.

At the moment, I am self funded so not a startup as such, but I am previous founder and my last gig was a distinguished engineer at Red Hat.

Let me know if this interests you, there will be a bucket load of bugs, so lots of fun to be had if anyone wants in!

where did I say I was convinced? I said I was not unconvinced. I am curious and not out-ruling anything, especially now that we have credible academic research starting on the matter.

Why are you convinced by a hobbyist with no academic background? He is a retired video game programmer.

The problem with your comment is you just lumped together a string of un-credible events and then summarise you're not convinced. To be frank Roswell and psyops (whatever that is) would not be enough to utterly convince me too. What I do find very interesting though is credible recent eye witness testimonies coming from US Navy pilots and the work at Harvard University for the Galileo Project, along with the other many recent activities around the study of UAPs (whatever they might be).

The problem as I see it with this area is it's been far too stigmatised, so no researchers would ever dare touch it for fear of being labelled conspiracy theory believing nutcases. That sentiment is now dying off thankfully and we can start to find out what on earth is going on.

very much. I have always worked in open source, so the joke has always been 'change of badge / laptop, but business as usual'. This is playing out widely now. Onboarding of a new worker now involves mailing a laptop and some swag to their house, getting them on a vpn, so they can be up and running in just a few days.

This reminds me of two things. British Weather and the The Myth of Sisyphus.

We have an old saying in the UK (it was popularised by an Austrian band, but it proceeds the song), "everywhere you go, you always take the weather with you'. In the UK it rains a lot, and folks think by going somewhere sunny it will resolve all their issues and lack of meaning in their life. Any change is fleeting and temporary.

The Myth of Sisyphus is a philosophical premise by Albert Camus. Sisyphus was a greek character who the gods had condemned to ceaselessly roll a rock to the top of a mountain, where the stone would fall back of its own weight. The gods believed there to be no more dreadful a punishment that is both futile and hopeless.

The central concern of The Myth of Sisyphus is what Camus calls "the absurd." or absurdism, a universe devoid of the meaning we long from it, as we toil through each day, repeating the mundane.

Camus claims that there is a fundamental conflict between what we want from the universe (meaning or order) and what we find in the universe (formless chaos, often devoid of meaning). We will never find in life itself the meaning that we want to find. Either we will discover a meaning through a leap of faith / dogma, by placing our hopes in a God beyond this world, or we will conclude that life is meaningless and be left with either suffering through or committing suicide.

In The Myth Of Sisyphus Camus claims that the only important philosophical question boils down to suicide and should we continue to live or not? The rest is secondary, because no one dies for scientific or philosophical arguments, they quickly abandon them when their life is at risk. Yet people do take their own lives because they judge them meaningless, or they sacrifice them for "meaningful" causes. This suggests that questions of meaning supersede all other scientific or philosophical questions. As Camus puts it: “I therefore conclude that the meaning of life is the most urgent of questions"

The point Camus is making is that there is no solution to the problem of living an absurd, meaningless existence. His argument is that the only way to confront it is to fully embrace the absurd, discard all hope, and live in revolt by throwing yourself so fully at a task in life that you lose yourself in the joy of the struggle.

Camus emphatically rejects any worldview that would leave us "at peace" with our existence. Our existence is an endless revolt against the Absurd, a 'fuck you' where we are fully aware of the meaninglessness of our lives yet choosing to live regardless.

I think this is the key aspect. For people with families at home, WFH is a godsend. I have two small children and am an avid runner on my local trails. WFH has meant I can get up around 7am and go running with my dog through the countryside, to then return, have a shower and walk with my young son to his school to drop him off. I can do all that and be showered and ready to start work in my home office by 9am.

Any companies not offering remote now that instead want me to commute to an office and lose all of that personal time, are an immediate rejection.

On the other hand, young professionals who have moved into a city and our just developing their career, they want to be among peers, socializing , learning and building a network.

That's my situation, we have a very globally diverse workforce from the UK, France, North America. I can only see this happening more and more over time now. Companies no longer need to restrict hiring to the small pool who are able to physically travel to a single location everyday.

I know what WASI is, my point is that there is no where near parity with existing posix implementations. I have been following the bytecode alliance and webassembly communities for a while and they can't seem to get beyond the design phase. You only need to look at the networking API [0] and the thread has not been updated for two months, with prior to that folks asking is the work even happening still

[0] https://github.com/WebAssembly/WASI/issues/370

One thing I am missing here. Docker, as much as it has the shortcomings you list, has an entire fleet of posix libraries, utils and tools at its availability. This has meant 99% of applications could wholesale lift their application and deploy it within a container. When I look at WASM/WASI there is no networking API, no storage API, crypto, etc etc. I can see its value for offloading parts of a web application that require a more speedy execution, but I cannot see anyway of running a full headless application which is where containers are hugely utilised right now.