Run frontier AI locally.

Bounded-integer 3SUM via exact NTT convolution, built while learning Rust, algorithms (w/ agents!)

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Per-collection OCR leaderboards using VLM-as-judge

⚡ Haystack + OpenSearch + Cognee — hybrid search, graph memory, streaming answers.

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Open-source inference server and production cluster for all the models your agent needs.

Community maintained hardware plugin for vLLM on Apple Silicon

Comprehensive ML/AI interview codex with iterative system design, production-ready code, and 2026 standards. Includes LLM/GenAI, RAG systems, agentic AI, and algorithms from scratch.

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

A framework for teaching AI to write like you. Not like a better version of you. Like you.

The best-benchmarked open-source AI memory system. And it's free.

Open-source AI job search: scan job portals, evaluate listings with a structured A-F rubric into a 1.0-5.0 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Cod…

A vector index built on TurboQuant, written in Rust with Python bindings

A high-throughput and memory-efficient inference and serving engine for LLMs

Code supporting the "Beyond Linearity in Attention Projections: The Case for Nonlinear Queries" paper

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

AI agents running research on single-GPU nanochat training automatically

A collection of tricks and tools to speed up transformer models

Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.

Presentation Slides for Developers

Material for gpu-mode lectures

Cost-efficient and pluggable Infrastructure components for GenAI inference

AirLLM 70B inference with single 4GB GPU

Beads - A memory upgrade for your coding agent

AI agents can now use real Android and iOS apps, just like a human.

Recursive Language Models (RLMs) implementation based on the paper by Zhang, Kraska, and Khattab