Seriously speaking, I feel the market is sorely lacking an Agent for the large number of existing devices running WinXP, Win7, and the like.
Not for developing on them, but for all kinds of debugging work it would be very useful; nowadays I'm used to just directing an Agent for everything.
Almost all agents require Windows 10 1809 or later. Debugging issues on older devices often turns out to be a real headache, and the only option is to get SSH working.
For old Windows, "setting up an SSH tunnel" itself takes quite a bit of fiddling. Especially when the device you need to deal with is on a distant external network, and you can't even remote in—you're limited to video calls and the like.
There are Golang ports for WXP and up (check the Reticulum-go GH repo and the users), and there's MIn-C as a port of core OBSD tools for XP (Unix tools, compiler, vi, openssh and a bunch more).
Couldn't agents just Remote Desktop or ssh into them?
For seriously older stuff, I'd run the disk image in a VM.
If they interact with legacy systems and/or virtualizing is no option and/or they have no internet access, a simple USB-to-COM adapter can create wonders. I remeber doing that on a win3.1 machine using TERMINAL.EXE many many years ago.
A typical scenario is that you walk into a small company and find they're still using Windows 7 or an early version of Windows 10. Then you have to help them deal with all sorts of problems.
In general, I've wondered whymost (all?) harnesses perform the API calls to the provider from the same machine that runs the tools. Why not have a client/server architecture? Then one session could talk to as many tool harnesses as it wanted to and you wouldn't have this kind of arbitrary limit of the session being tied to one specific workspace.
My harness actually has 3 distinct components: the LLM gateway, the agent session manager, and the tool server, and they can be run on different machines. The most obvious use case is the LLM gateway being a central router for all provider queries with multiple machines running the agent sessions.
The agent session manager talks to the LLM gateway over HTTP using a standard internal protocol, then the gateway has adapters for each upstream provider and translates between their external API format and the standard internal one.
The tool server is a separate jar running as a separate server process with its own systemd unit and the agent session manager talks to the tool server over a beanstalkd queue. The primary motivation for having 2 processes was total separation for unprivileged agent tool call execution (ie. the tool server systemd unit runs as a user with no sudo whereas the agent session manager can execute as root, so the user can run scripts through the interface that do things like install packages and access secrets, but the agent can't do that.
The tool server could just as easily be talking to beanstalkd over a Cloudflare tunnel or ssh port forward, though, and a session could be routed to different machines, allowing execution of tool calls in different environments within the same context window/agent session.
Man the first thing that came to my mind was. From this stage if we ask AI to self build to current windows OS or Mac level. I can't help but put this fake scenario in my mind that imagine if we had this back in the day.
It feels very cute and mischievous to start agents in unusual environments (DOS, Linux running on a feature phone, Windows 95, etc) and see how they react :)
Yep, I've made one in win32 earlier this month for that exact reason. It's always amusing seeing DeepSeek's CoT realise it's running inside NT 4.0 once it does a directory listing. It handles it pretty well too, I gave it a intentionally broad prompt to "write a 3d shooter game" pretty much, and it went and found the DirectX SDK that comes with VS6 and oneshotted it.
Seriously speaking, I feel the market is sorely lacking an Agent for the large number of existing devices running WinXP, Win7, and the like. Not for developing on them, but for all kinds of debugging work it would be very useful; nowadays I'm used to just directing an Agent for everything.
Almost all agents require Windows 10 1809 or later. Debugging issues on older devices often turns out to be a real headache, and the only option is to get SSH working.
But should not AI be able to solve all these mentioned problems? Why can they not solve that?
It would not make a whole lot of sense to me.
For old Windows, "setting up an SSH tunnel" itself takes quite a bit of fiddling. Especially when the device you need to deal with is on a distant external network, and you can't even remote in—you're limited to video calls and the like.
There are Golang ports for WXP and up (check the Reticulum-go GH repo and the users), and there's MIn-C as a port of core OBSD tools for XP (Unix tools, compiler, vi, openssh and a bunch more).
Couldn't agents just Remote Desktop or ssh into them?
For seriously older stuff, I'd run the disk image in a VM.
If they interact with legacy systems and/or virtualizing is no option and/or they have no internet access, a simple USB-to-COM adapter can create wonders. I remeber doing that on a win3.1 machine using TERMINAL.EXE many many years ago.
A typical scenario is that you walk into a small company and find they're still using Windows 7 or an early version of Windows 10. Then you have to help them deal with all sorts of problems.
In general, I've wondered whymost (all?) harnesses perform the API calls to the provider from the same machine that runs the tools. Why not have a client/server architecture? Then one session could talk to as many tool harnesses as it wanted to and you wouldn't have this kind of arbitrary limit of the session being tied to one specific workspace.
My harness actually has 3 distinct components: the LLM gateway, the agent session manager, and the tool server, and they can be run on different machines. The most obvious use case is the LLM gateway being a central router for all provider queries with multiple machines running the agent sessions.
The agent session manager talks to the LLM gateway over HTTP using a standard internal protocol, then the gateway has adapters for each upstream provider and translates between their external API format and the standard internal one.
The tool server is a separate jar running as a separate server process with its own systemd unit and the agent session manager talks to the tool server over a beanstalkd queue. The primary motivation for having 2 processes was total separation for unprivileged agent tool call execution (ie. the tool server systemd unit runs as a user with no sudo whereas the agent session manager can execute as root, so the user can run scripts through the interface that do things like install packages and access secrets, but the agent can't do that.
The tool server could just as easily be talking to beanstalkd over a Cloudflare tunnel or ssh port forward, though, and a session could be routed to different machines, allowing execution of tool calls in different environments within the same context window/agent session.
Agreed. Kind of strange how AI promises everything but the old platforms are still ignored and neglected.
I've got an agent that just uses legacy perl 5.0001 ... close but there's no perl by default on windows (although it's easy enough to get on there)
https://github.com/kristopolous/old-agent
I've used it on plenty of old things.
I'd probably do a pure .vbs version if it was windows or a static pure win32 exe.
https://github.com/xmeadow/igor runs on react OS but was tested on XP and win7. Works flawlessly.
I wonder what kind of sandboxing you'd get on those machines though. Likely nought.
Sandboxing would defeat the point of using agents on these machines, though.
I wonder how far people could take DOS with today's knowledge.
Man the first thing that came to my mind was. From this stage if we ask AI to self build to current windows OS or Mac level. I can't help but put this fake scenario in my mind that imagine if we had this back in the day.
Nice, is it claude only or could it also use codex?
It feels very cute and mischievous to start agents in unusual environments (DOS, Linux running on a feature phone, Windows 95, etc) and see how they react :)
Yep, I've made one in win32 earlier this month for that exact reason. It's always amusing seeing DeepSeek's CoT realise it's running inside NT 4.0 once it does a directory listing. It handles it pretty well too, I gave it a intentionally broad prompt to "write a 3d shooter game" pretty much, and it went and found the DirectX SDK that comes with VS6 and oneshotted it.
DeepSeek is also wonderful for salvaging old phones for creating personal dashboard or silly handheld gaming machines.
Put one inside Red Star OS and watch it take out the power grid!
I have to say this is really creative to try create a coding agent on DOS!
Does this prove that Claude Code doesn't have to be shipped as 200MB binaries?
SCNR: Could someone please rewrite this in Go and call the result Gla(w)DOS?
This can maybe optimize config.sys/autoexec.bat memory usage
I love what I see!
prob. many people dont even know what DOS is anymore :D
Making DOS great again!
Finally it can outperform TempleOS.
Someone should rewrite the old Lemmings game with AI as well.