An application stack Claude coded directly in LLVM IR
This repo is the result of a debate about what kind of programming language might be appropriate if humans are no longer the primary authors. Initially the thought was "LLMs can just generate binaries directly" (this was before a more famous person had the same idea). But that on reflection seems like a bad approach because languages exist to capture program semantics that are elided by translation to machine code. The next step was to wonder if an existing "machine readable" program representation can be the target for LLM code generation. It turns out yes. This project is the result of…
An application stack Claude coded directly in LLVM IR launched on March 12, 2026 with 10 votes, #1,177 of 23,380 launches that month and more than 90% of that year's launches.
In plain words
This project explores AI-generated code by having Claude write an entire application stack directly in LLVM intermediate representation. Rather than generating binaries or high-level languages, the creator chose LLVM IR as a machine-readable target that preserves program semantics. The experiment demonstrates whether LLMs can effectively produce complex software systems in this lower-level representation format, addressing questions about what programming languages are appropriate when AI systems are the primary authors.
written from the facts on this page · September 2026
From the sources
Contribute to superfield-ai/alien-stack development by creating an account on GitHub.
Alien Stack is an architecture for agent-native software development , described in detail in the Alien Stack Whitepaper . It's intentionally alien. The paper imagines a future where humans stop writing text-based source code to align with human cognitive constraints. Instead direct agent coders to generate artifacts which have semantic representations of programs. We explored here how the LLVM Intermediary Representation could today provide much of that for agents. Then we add a thin framework to provide guardrails for the agent and program: the graph structure, formal verification, and effects. The stack doesn't propose an end state. It shows what is possible with the constraints of agent…from github.com
In the maker’s words, at launch
This repo is the result of a debate about what kind of programming language might be appropriate if humans are no longer the primary authors. Initially the thought was "LLMs can just generate binaries directly" (this was before a more famous person had the same idea). But that on reflection seems like a bad approach…
Does a similar job
all alternatives →
Why write code if the LLM can just do the thing? (web app experiment)Nov 2025 · github.com · ▲436I spent a few hours last weekend testing whether AI can replace code by executing directly. Built a contact manager where every HTTP request goes to an LLM with three tools: database (SQLite), webResponse (HTML/JSON/JS), and updateMemory (feedback). No routes, no controllers, no business logic. The AI designs schemas on first request, generates UIs from paths alone, and evolves based on natural language feedback. It works—forms submit, data persists, APIs return JSON—but it's catastrophically slow (30-60s per request), absurdly expensive ($0.05/request), and has zero UI…
Fork of Claude-code working with local and other LLM providers2025 · github.com · ▲177
Prompts as WASM Programs2024 · github.com · ▲209AICI is a proposed common interface between LLM inference engines (llama.cpp, vLLM, HF Transformers, etc.) and "controllers" - programs that can constrain the LLM output according to regexp, grammar, or custom logic, as well as control the generation process (forking, backtracking, etc.). AICI is based on Wasm, and is designed to be fast (runs on CPU while GPU is busy), secure (can run in multi-tenant cloud deployments), and flexible (allow libraries like Guidance, LMQL, Outlines, etc. to work on top of it). We (Microsoft Research) have released it recently, and would love feedback on the…
LLM, a Rust Crate/CLI for CPU Inference of LLMs (LLaMA, GPT-NeoX, etc.)2023 · github.com · ▲45G'day, HN! I'm one of the maintainers of `llm`. I've been working alongside a trusty group of contributors to bring this project to life, and we're now at a point where we're ready to share it with the world. Large language models (LLMs) are taking the computing world by storm due to their emergent abilities that allow them to perform a wide variety of tasks, including translation, summarization, code generation, and even some degree of reasoning. However, the ecosystem around LLMs is still in its infancy, and it can be difficult to get started with these models. `llm` is a one-stop shop for…
CodeRLM – Tree-sitter-backed code indexing for LLM agentsFeb 2026 · github.com · ▲81I've been building a tool that changes how LLM coding agents explore codebases, and I wanted to share it along with some early observations. Typically claude code globs directories, greps for patterns, and reads files with minimal guidance. It works in kind of the same way you'd learn to navigate a city by walking every street. You'll eventually build a mental map, but claude never does - at least not any that persists across different contexts. The Recursive Language Models paper from Zhang, Kraska, and Khattab at MIT CSAIL introduced a cleaner framing. Instead of cramming everything into…
Marvin – build AI functions that use an LLM as a runtime2023 · github.com · ▲127Hey HN! We're excited to share our new open-source project, Marvin. Marvin is a high-level library for building AI-powered software. We developed it to address the challenges of integrating LLMs into more traditional applications. One of the biggest issues is the fact that LLMs only deal with strings (and conversational strings at that), so using them to process structured data is especially difficult. Marvin introduces a new concept called AI Functions. These look and feel just like regular Python functions: you provide typed inputs, outputs, and docstrings. However, instead of relying on…
Questions this answers
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
