someguy101010

its not marketing to you, its marketing to agents looking for tools to use

You may have heard of Programmatic Tool Calling from anthropic or Code Mode from cloudflare for calling mcp servers. I have been working on an open source version of this and recently put together some basic docs, and thought this page would be a good one to share.

There are plenty of other features to explore, but this one alone has resulted in significant improvements in the speed of execution in many tasks including minecraft playing agents, computer use agents, and for querying and aggregating information from my telemetry systems in a lightweight low risk way.

if i didn't have to prompt it to learn from its mistakes and it just "intuitively" knew to do that

have built in this space which led me to develop a minizinc mcp server [0] for scheduling bocce tournaments [1]. scheduling with constraints is a np hard problem and it makes sense people struggle. tools exist to solve this problem but they are complex and hard to use for non technical folks, and even technical folks. am hoping a tool like this can bridge the gap and would like to bring it to your awareness if you aren't already thinking about the problem this way :)

edit: after reading a bit more of description looks like yall are taking a similar approach, kudos!

[0] https://github.com/r33drichards/minizinc-mcp

[1] https://github.com/r33drichards/bocce-scheduler

yep! thats the motivation behind https://github.com/r33drichards/mcp-js

I want to be able to give agents access to computation in a secure way without giving them full access to a computer

Does this support bedrock?

Is it possible to provide a llm a skill through the mcp resource feature?

as an infrastructure engineer the idea of being able to train computer use agents without provisioning infrastructure sounds amazing!

a common use case i run into is i want to be able to configure corporate vpn software on windows machines. is there a link for a getting started guide i could try this out with?

have used it, and i do like it, but the licensing situation is not great. It open source but its not free software by any means.

wrote about this a bit too in https://www.robw.fyi/2025/10/24/simple-control-flow-for-auto...

ran into this when writing agents to fix unit tests. often times they would just give up early so i started writing the verifiers directly into the agent's control flow and this produced much more reliable results. i believe claude code has hooks that do something similar as well.

clearly you have never worked in enterprise

nice one kyle! you could add https://github.com/wasmerio/webassembly.sh and have a fully featured in browser shell with support for installing packages!

reposting this from youtube comment

From 1:14:55-1:15:20, within the span of 25 seconds, the way Demis spoke about releasing all known sequences without a shred of doubt was so amazing to see. There wasn't a single second where he worried about the business side of it (profits, earnings, shareholders, investors) —he just knew it had to be open source for the betterment of the world. Gave me goosebumps. I watched that on repeat for more than 10 times.

I opt for the greedy strategy in most game play scenarios for pretty much the reasons you described here. I was considering making a mod to perform this action for me and was looking for a more "correct" solution but greedy is way simpler and just as effective for most cases.

Thanks for catching this!

if the people who develop and release these models were all optimizing for the same goals, they could converge on strategies or behaviors, without coordinating.

Does it matter if the code is messy?

It matters proportionally to the amount of time I intend to maintain it for, and the amount of maintenance expected.

Thanks but its not mine! I just found it inspirational.

How does the agent know which to keep and which to discard for a conflict? This would that it has deep contextual information about the codebase it's looking at.

There is no guidance regarding this in the agent. For some conflicts this is important but I have found that for the conflicts I've tried this on it does not need the additional context to do the right thing! There is a option to add additional prompting before it solves a conflict. I will add notes in here to guide it such as "ignore auto generated files, i will generate them again later" so that it doesn't get stuck on generated data.

https://github.com/r33drichards/mcp-js mcp for running javascript locally and safely using v8

Thank you for the detailed response!

Thanks for sharing this! A couple of questions come to mind:

- How does training with RL differ from fine tuning?

- When would it make sense to fine tune instead of using RL?

The No Free Lunch Theorem implies that something like this is inevitable https://en.wikipedia.org/wiki/No_free_lunch_in_search_and_op...

Nice! I'm working on a way to do this for javascript using v8 https://github.com/r33drichards/mcp-js. Right now this works but there is some significant jank.

graalvm

I also enjoyed this in video format https://youtu.be/JLlIAWjvHxM?feature=shared&t=2049

Always have been envious of that performance testing setup that is shown here

I'll just provide a quick counter to this based on my own experience.

A few years ago I had been in my best shape (daily exercise, cardio and weight lifting) and started experiencing some forearm pain. I thought it was just from over use from typing but i finally went to a physical therapist and found that the pain came from me hunching over on my computer and putting a lot of strain on my fore arms. The posture I took on was a combination of

1. Just leaning in to my computer because I'd be trying to read text or getting "into" whatever i'm working on

2. My upper back not having the endurance or development that I needed to hold up my upper body.

I had to change my exercise routine to give my muscles more endurance to hold my upper back up while seated.

So yea, exercise is definitely going to help but I wouldn't just say it fixes things automagically for you and you could run into posture issues even when you are doing the right things in life. :)

any plans to open source? I feel very comfortable using neon.tech (separates compute from storage for postgres) b/c they open source their stack but it would be hard for me to adopt something like oodle without an open source version.

this installer comes with an uninstaller https://install.determinate.systems/

Nice! I'll have to read through this and use it to improve https://brev.dev/blog/how-to-win-a-2-player-game-of-are-you-... which was a similar exercise on a game slightly different than prisoners dilemma. I like being able to use "brute force" numerical methods to solve problems like this because they are often simpler to construct and exploit the fact that computers go brrr.

If you use nixos there's also https://github.com/nlewo/comin