Hacker News: schmuhblaster

"Compile" Markdown specs for SDD or Subagents into executable logic, e.g. CodeAct+DSPy+Prolog. Not sure how and if I will continue, but it's been lots of fun.

New comment by schmuhblaster in "OpenClaw is changing my life"

schmuhblaster — Mon, 09 Feb 2026 02:58:06 +0000

I'd be curious if a middle layer like this [0] could be helpful? I've been working on it for some time (several iterations now, going back and forth between different ideas) and am hoping to collect some feedback.

[0] https://github.com/deepclause/deepclause-sdk

"Compiled" Specs

schmuhblaster — Sun, 08 Feb 2026 07:52:55 +0000

Article URL: https://deepclause.substack.com/p/compiled-specs

Comments URL: https://news.ycombinator.com/item?id=46932268

Points: 1

# Comments: 0

New comment by schmuhblaster in "Show HN: AgentVM – Safe, Sandboxed Linux VM for OpenClaw and AI Agents"

schmuhblaster — Fri, 06 Feb 2026 01:50:17 +0000

Network can be closed down. It also uses a userland network stack, so future iterations might include being able to define rules for ingress and egress.

New comment by schmuhblaster in "The Missing Layer"

schmuhblaster — Thu, 05 Feb 2026 14:49:14 +0000

I've been recently experimenting with using a Prolog-based DSL [0] as the missing layer: Start with a markdown document, "compile" it into the DSL, so that you obtain an "executable spec". Execution still involves LLMs, so it's not entirely deterministic, but it's probably more reliable than hoping your markdown instructions get interpreted in the right way.

[0] https://github.com/deepclause/deepclause-sdk

Backtracking Through Agent Memory – Adventures with LLMs, Prolog and DeepClause

schmuhblaster — Thu, 05 Feb 2026 14:25:53 +0000

Article URL: https://deepclause.substack.com/p/backtracking-through-memory

Comments URL: https://news.ycombinator.com/item?id=46899956

Points: 2

# Comments: 0

New comment by schmuhblaster in "Coding Agent VMs on NixOS with Microvm.nix"

schmuhblaster — Thu, 05 Feb 2026 05:37:21 +0000

Or try this: https://github.com/deepclause/agentvm, it's based on container2wasm, so the VM is fully defined by a Dockerfile.

New comment by schmuhblaster in "Sandboxing AI Agents in Linux"

schmuhblaster — Wed, 04 Feb 2026 09:01:28 +0000

My attempt at a portable solution: Linux VM inside WASM for sandboxed execution: http://agentvm.deepclause.ai

Minimal dependencies, but not as fast as containers or bubblewrap.

New comment by schmuhblaster in "Show HN: DeepClause CLI – Compile Markdown specs into executable logic programs"

schmuhblaster — Tue, 03 Feb 2026 15:47:13 +0000

Hi all, been building this in public for some time. This is my latest iteration, hoping to get some interesting comments and feedback here, before I go down yet another rabbit hole and unnecessarily burn through even more premium tokens.

Show HN: DeepClause CLI – Compile Markdown specs into executable logic programs

schmuhblaster — Tue, 03 Feb 2026 15:47:13 +0000

Article URL: https://github.com/deepclause/deepclause-sdk

Comments URL: https://news.ycombinator.com/item?id=46872468

Points: 1

# Comments: 1

New comment by schmuhblaster in "Show HN: Amla Sandbox – WASM bash shell sandbox for AI agents"

schmuhblaster — Fri, 30 Jan 2026 15:32:10 +0000

Thank you! When I started working on agentvm my original goal was similar to yours, build a kind of Mingw or Cygwin for WASM. However, I quickly learned that this wouldn't really be feasible with reasonable amounts of time/token spend, mostly due to issues like having to find a way to make fork work, etc. I am no expert for WASM or Linux system programming, but it's been a lot of fun working on this stuff. I hope that the WASI standard and runtimes become more mature, as I feel that WASM sandboxes make a lot of sense in environments where containers are not an option.

New comment by schmuhblaster in "Show HN: NPM install a WASM based Linux VM for your agents"

schmuhblaster — Tue, 20 Jan 2026 01:55:00 +0000

linux-wasm is an awesome project, but relies on compiling the kernel itself into WASM. This seems to work in principle, but is still a bit unstable. But I do hope that eventually one can get rid of the emulator in the middle as is done in c2w.

New comment by schmuhblaster in "Show HN: NPM install a WASM based Linux VM for your agents"

schmuhblaster — Tue, 20 Jan 2026 00:15:02 +0000

Thought this could be useful. Opus 4.5 helped me build most of it, including a simple network stack so that the VM may access the outside world. Still at a very early stage, but I think it looks promising.

Show HN: NPM install a WASM based Linux VM for your agents

schmuhblaster — Tue, 20 Jan 2026 00:12:05 +0000

Article URL: https://github.com/deepclause/agentvm

Comments URL: https://news.ycombinator.com/item?id=46686346

Points: 3

# Comments: 3

New comment by schmuhblaster in "My Gripes with Prolog"

schmuhblaster — Fri, 16 Jan 2026 13:24:26 +0000

Opus 4.5 helped me implement a basic coding agent in a DSL built on top of Prolog: https://deepclause.substack.com/p/implementing-a-vibed-llm-c.... It worked surprisingly well. With a bit of context it was able to (almost) one-shot about 500 lines of code. With older models, I felt that they "never really got it".

New comment by schmuhblaster in "My Gripes with Prolog"

schmuhblaster — Fri, 16 Jan 2026 10:31:31 +0000

>> I think much of the frustration with older tech like this comes from the fact that these things were mostly written(and rewritten till perfection) on paper first and only the near-end program was input into a computer with a keyboard.

I very much agree with this, especially since Prolog's execution model doesn't seem to go that well with the "successive approximations" method.

New comment by schmuhblaster in "My Gripes with Prolog"

schmuhblaster — Fri, 16 Jan 2026 07:46:51 +0000

I also have a strange obsession with Prolog and Markus Triska's article on meta-interpreters heavily inspired me to write a Prolog-based agent framework with a meta-interpreter at its core [0].

I have to admit that writing Prolog sometimes makes me want to bash my my head against the wall, but sometimes the resulting code has a particular kind of beauty that's hard to explain. Anyways, Opus 4.5 is really good at Prolog, so my head feels much better now :-)

[0] http://github.com/deepclause/deepclause-desktop