Stars
Async conflict-aware spec/planning, for me, you and your LLM/agent
Anthropic's original performance take-home, now open for you to try!
A curriculum for learning about gpu performance engineering, from scratch to what the frontier AI labs do
Faithful reproduction of "VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs" https://arxiv.org/abs/2512.12072 https://arxiv.org/pdf/2512.12072
Reproduction study of Grassmann Flows for sequence modeling (arXiv 2512.19428). Shows 22.6% gap vs claimed 10-15%, includes CUDA kernels with 2x speedup.
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
⚡ The AI Slop Index linter inspired by @karpathy. Detects hallucinated imports, any-type abuse, vibe coding, and soul-less patterns in TypeScript/JavaScript/React. Fast (~4s), educational, CI-ready…
Postgres extension for vector search (DiskANN), complements pgvector for performance and scale. Postgres OSS licensed.
an agentic research assistant
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
Solve more puzzles. Further improve your tensor programming skills.
Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
Convert math-rich Typst project to Microsoft Word format
Open-Source Dual-Arm Mobile Robot with Motorized Lift
A discord frontend for Codex CLI and Claude Code [mirror]
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Fine-tune ModernBERT with custom tokenizers, curriculum learning, and next-gen optimizers.
Open Human Ontology: A collaborative project to build a comprehensive, open, and structured human ontology for research and applications in AI and knowledge management.