Tag

DFlash: Block Diffusion for Flash Speculative Decoding

Enables parallel speculative decoding by using a lightweight block-diffusion draft model to produce multi-token drafts for faster, high-quality generation. Integrates with vLLM, SGLang and Transformers backends and ships draft models on Hugging Face.

UI Skills

Provides a set of versioned "skills" that codify UI design standards and automated checks for design engineers and AI agents. Includes a CLI to discover, install, and run skills like baseline UI rules, accessibility fixes, motion-performance tuning, and metadata corrections.

Headroom

Compresses any context sent to LLMs (tool outputs, DB reads, RAG results, files, logs) to cut tokens by ~70–95% while preserving reversible originals; runs as a proxy or Python/TypeScript SDK with integrations for common agent frameworks.

OpenReel Video

Browser-based, client-side video editor for multi-track editing, GPU-accelerated preview and local exports without uploading files; leverages WebCodecs/WebGPU and includes an AI upscaling option.

Agent Skills

Reusable skills—instructions plus helper scripts—that extend AI coding agents. Covers Vercel deployment audits, React performance rules, UI accessibility checks, and writing guidelines; each loads only when a relevant task appears.

Nemotron-SFT-Math-v3

Large-scale mathematical reasoning dataset of model-generated solution trajectories produced with and without Python Tool-Integrated Reasoning (TIR), with final answers verified against reference solutions. Contains ~3.64M JSONL training samples (~144 GB) and per-source CC-BY / CC-BY-SA licensing; intended for training and evaluating tool-augmented mathematical reasoning in LLMs.

OpenViking

Models an AI agent's context as a file system, unifying memory, resources, and skills instead of flat vector RAG. Uses L0/L1/L2 tiered loading to cut tokens, directory-recursive plus semantic retrieval, and visualized retrieval traces for debugging.

INFINI-NEWS Corpus

Processed, multilingual news corpus of 1.357B articles extracted from Common Crawl CC‑News with per-article WARC provenance. Includes trafilatura-extracted bodies, language labels (GlotLID & CommonLingua), IPTC topic tags, monthly Parquet shards and a companion FM-index for sub-10ms substring queries; bulk text access is gated for academic research.

Anima

Generates anime-style and other non-photorealistic illustrations from text prompts. A 2B-parameter diffusion base preview trained on millions of anime images (and ~800k non-anime art) and released under a non-commercial license; best used in ComfyUI around ~1MP resolution.

NVIDIA Agent Skills

Provides a catalog of NVIDIA-verified, portable “skills” — instruction sets that teach AI agents how to use NVIDIA libraries, models and platform tools. Each skill is published with detached signatures and evaluation artifacts for verifiable reuse in agent workflows.

Evolver

Generates protocol-bound GEP prompts that guide iterative evolution of AI agent behavior from runtime logs, producing auditable EvolutionEvents and reusable Genes/Capsules. Node.js-based and works offline; optional EvoMap network integration enables skill sharing, worker pools and leaderboards while git provides rollback and validation.

OpenClaw Mission Control

Centralized operations dashboard for OpenClaw agent fleets — orchestrate boards and tasks, manage agent lifecycles, enforce approval-driven governance, and operate gateway-connected runtimes from a single UI and API.