# LLVM Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/llvm
> Markdown URL: https://aitinkerers.org/technologies/llvm.md
> Technology record last updated: 2026-02-24T06:28:11Z
> Generated: 2026-09-21T16:46:17Z

LLVM is a modular compiler and toolchain infrastructure, providing reusable, language-agnostic components for high-performance compilation and optimization.

LLVM is a collection of modular compiler and toolchain technologies, designed for maximum reusability and performance. Its core is the Intermediate Representation (IR), a portable, high-level assembly that acts as the optimization target between the frontend and backend stages. This three-part architecture allows projects like Clang (for C/C++) and compilers for Swift and Rust to share a single, powerful optimization and code generation engine. This flexibility enables efficient, cross-platform compilation for diverse architectures: from x86 and ARM to GPUs, making LLVM a foundational component in modern operating systems and development toolchains.

- Official technology site: https://llvm.org
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Building a Persistent Memory & Stateful Second Brain AI Agent](https://dhaka.aitinkerers.org/talks/rsvp_kSMaLnvvGGg)

Demonstrating context engineering in practice through Slatekore - an open-source starter kit that gives Gemini CLI persistent memory using Obsidian as the storage layer. 1. State Management Without Infrastructure How to use the file system as persistent state - your Obsidian vault becomes both the agent's memory and its knowledge base. No databases, no vector stores, no MLOps. 2. Context Engineering for Agent Behavior Crafting system prompts (GEMINI.md) and workflow files that define agent capabilities, constraints, and multi-step reasoning patterns. The prompt is the agent's configuration. 3. Tool Use Through Natural Interfaces Connecting the agent to real actions: creating files, managing tasks, building knowledge graphs - all through natural language commands backed by structured templates. Watch a stateful agent capture research, recall context from previous sessions, update its knowledge graph, and execute project workflows - without any model training or fine-tuning.

- Event context: AI Tinkerers Dhaka 2nd Meetup: Dhaka Builds with AI! — 2026-02-07 — Dhaka
- Public talk page: https://dhaka.aitinkerers.org/talks/rsvp_kSMaLnvvGGg

### [Hacking autodiff into the Rust compiler](https://toronto.aitinkerers.org/talks/rsvp_sfMIhuRtDYo)

I will start by showing everyone how simple it is to compile your own Rust compiler with support for automatic differentiation enabled. Due to time constraints, I will just show the commands, and not run the actual build. Next, we want to see it working, so I will compile some Rust code into the LLVM Intermediate Representation (IR) and show how our tool for automatic differentiation rewrites the IR to compute derivatives. I will show the different IR rewrite steps to explain why LLVM is usually very efficient here, and what is currently the best way to crash it. As a final, bigger example I will introduce a Rusty version of Karpathy's llm.c model which was auto-translated by rust2c. With `git show` I will go through a diff which deletes hundreds of lines from Karpathy that implemented backpropagation manually, since we can replace them with a single line of std::autodiff. I will then run the code to train the model.

- Event context: AI Tinkerers Toronto - March 2025 Meetup at Mozilla — 2025-03-27 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_sfMIhuRtDYo

## Related Technologies

- [AI agent](https://aitinkerers.org/technologies/ai-agent) ([Markdown](https://aitinkerers.org/technologies/ai-agent.md)) — 8 public demos
- [ARM](https://aitinkerers.org/technologies/arm) ([Markdown](https://aitinkerers.org/technologies/arm.md)) — 1 public demo
- [AVX2](https://aitinkerers.org/technologies/avx2) ([Markdown](https://aitinkerers.org/technologies/avx2.md)) — 1 public demo
- [Enzyme](https://aitinkerers.org/technologies/enzyme) ([Markdown](https://aitinkerers.org/technologies/enzyme.md)) — 1 public demo
- [GCC](https://aitinkerers.org/technologies/gcc) ([Markdown](https://aitinkerers.org/technologies/gcc.md)) — 1 public demo
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Gemini CLI](https://aitinkerers.org/technologies/gemini-cli) ([Markdown](https://aitinkerers.org/technologies/gemini-cli.md)) — 16 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [LLVM IR](https://aitinkerers.org/technologies/llvm-ir) ([Markdown](https://aitinkerers.org/technologies/llvm-ir.md)) — 1 public demo
- [Markdown](https://aitinkerers.org/technologies/markdown) ([Markdown](https://aitinkerers.org/technologies/markdown.md)) — 24 public demos
- [Obsidian](https://aitinkerers.org/technologies/obsidian) ([Markdown](https://aitinkerers.org/technologies/obsidian.md)) — 6 public demos
- [Prompt Engineering](https://aitinkerers.org/technologies/prompt-engineering) ([Markdown](https://aitinkerers.org/technologies/prompt-engineering.md)) — 28 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [RISC-V](https://aitinkerers.org/technologies/risc-v) ([Markdown](https://aitinkerers.org/technologies/risc-v.md)) — 1 public demo
- [Rust](https://aitinkerers.org/technologies/rust) ([Markdown](https://aitinkerers.org/technologies/rust.md)) — 56 public demos
- [rust2c](https://aitinkerers.org/technologies/rust2c) ([Markdown](https://aitinkerers.org/technologies/rust2c.md)) — 1 public demo
- [SSE](https://aitinkerers.org/technologies/sse) ([Markdown](https://aitinkerers.org/technologies/sse.md)) — 4 public demos
- [System prompt](https://aitinkerers.org/technologies/system-prompt) ([Markdown](https://aitinkerers.org/technologies/system-prompt.md)) — 2 public demos