Discover the Best AI Resources

SMOL

Provides professionally translated parallel corpora and a multilingual lexicon across 100+ low-resource languages for training and evaluating multilingual MT and NLP models. Includes SmolDoc, SmolSent, GATITOS, and factuality annotations; licensed CC-BY-4.0.

Awesome AI Apps

Curates 80+ hands-on LLM-powered examples, tutorials and recipes for building agents, RAG systems, voice assistants, and agentic workflows. Includes starter templates, course playlists, and reference apps for rapid prototyping and learning.

DeepEP

Provides high-throughput, low-latency GPU communication kernels for Mixture-of-Experts (MoE) and expert-parallel workloads, with NVLink↔RDMA-aware forwarding, FP8/BF16 support, and low-latency RDMA hooks for inference decoding.

PRIME-RL

An asynchronous, high-throughput framework for large-scale reinforcement learning and agentic training that scales to 1T+ MoE models and 1000+ GPUs, with native verifiers integration, end-to-end SFT/RL/evals, and Slurm/Kubernetes deployment; requires NVIDIA GPUs.

Pyrefly

Performs fast static type checking and provides a language server with code navigation, semantic highlighting, and completions for Python. Processes ~1.85M lines/sec and completes IDE rechecks typically under 10ms — intended for responsive editor workflows and large codebases.

Interaction2Code

A benchmark dataset for evaluating MLLM-driven interactive webpage code generation: provides prototyping screenshots, action.json interaction metadata, and example generation scripts across 127 webpages and 374 interactions to test dynamic UI-to-code capabilities.

FlashMLA

Optimized MLA (Multi-head Latent Attention) decoding kernels powering DeepSeek-V3/V3.2 inference on Hopper and Blackwell GPUs. Dense decoding reaches ~3000 GB/s and 660 TFLOPS on H800; the sparse path stores the KV cache in FP8.

AiToEarn

Distributes one post across 14+ platforms (Douyin, Xiaohongshu, TikTok, X), automates likes and replies via a browser plugin, and matches creators to paid brand tasks settled by sales, views, or engagement. Drivable from Claude/Cursor via MCP.

AReaL

Trains LLM reasoning and agentic models with fully asynchronous reinforcement learning, decoupling rollout generation from policy updates for a 2.77x speedup over synchronous RL. Covers GRPO, PPO and DAPO across Megatron, FSDP, vLLM and SGLang backends.

Hands-On AI Engineering

Curated collection of production-oriented AI projects that implement OCR, RAG, multi-agent systems, and multimodal pipelines. Each entry provides runnable code, setup notes, and engineering patterns to help developers move prototypes toward production.

ComfyUI-WanVideoWrapper

Wraps Alibaba's Wan text/image-to-video models and many derivatives (SkyReels, WanAnimate, MultiTalk, Phantom) as ComfyUI nodes, adding FP8 scaling, block swapping and context windows for 1000+ frame clips.

Claude Code Router

Provides a local model gateway and control plane for coding agents — route Claude Code, Codex, Grok CLI, ZCode and compatible clients to multiple providers through one stable local endpoint while managing routing, failover, tools, credentials, and observability.