Results for “nemo-curator”

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

Guides AI coding assistants to the official NemoClaw documentation via MCP server or Markdown files for installation, configuration, operation, and troubleshooting.

Index folders of PDFs and other documents into LanceDB for vector search, then query them with semantic search, page filters, verbatim quotes, and cross-document aggregation.

Run evaluation tasks against a NeMo Platform server using the Evaluator plugin CLI and Python SDK.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.

Configure fault tolerance, straggler detection, preemption, in-process restart, and re-run state machine for Megatron Bridge training jobs.

Generates custom safety policies for NVIDIA Nemotron content-safety guardrails, producing a Markdown policy, JSON taxonomy, and inference prompts from rough user input.

Plan, configure, and chain Nemotron model customization steps into single-step or multi-step pipelines for curation, translation, fine-tuning, RL alignment, benchmarking, checkpoint conversion, optimization, and evaluation.

Plan, debug, tune, evaluate, export, or deploy public Nemotron embedding and reranking retrieval recipes using the current checkout.

Maintain durable session memory across agent disconnects by writing structured checkpoints to the repo's session directory, enabling context recovery.

Convert single-node PyTorch distributed scripts into multi-node Slurm sbatch jobs and debug common multi-node failures, covering srun-native and torch.distributed approaches, container setup, NCCL timeouts, and interactive allocation.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

Segundo agente do Time de Migração. Decide o que migra, o que descarta e o que precisa de decisão humana, com base nas specs do legado, no critério do brief e no paradigma escolhido. Produz target_business_rules.md e discard_log.md. Ativação: /reversa-curator (geralmente invocado por /reversa-migrate).

Drive Moli (`moli`), Lexmount's open-source headless browser for AI agents, built around on-demand rendering: real JavaScript, DOM, and CSS by default, with layout and pixels computed only when explicitly requested via `--layout`. Use when the user wants to fetch/extract a live JavaScript-rendered page as Markdown/HTML/JSON/semantic-tree, capture a screenshot or PDF, run a small bounded crawl, start a CDP/WebDriver automation server for Playwright/Puppeteer, replace a Chromium/ChromeDriver dependency, or diagnose readiness/network/frame issues on a rendered page. Triggers on: "moli fetch", "moli serve", "headless browser for agents", "on-demand rendering browser", "CDP server without Chrome", "structure-first web scraping", "Lexmount browser", "moli-webfetch", "moli-cdp-server".

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

Curating cross-agent knowledge and institutional memory: extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices. Use for memory curation.

杰诺斯（少年漫）认知与表达框架（压缩蒸馏）：改造人认真、战损美学、师徒忠犬 触发：一拳超人 等。虚构

Post-execution skill crystallization and learning engine updates for WinDAGs. Runs after successful execution to update Thompson sampling parameters, track method quality, detect monster-barring, log near-miss events, and signal Kuhnian crises. Activate on "curator", "learning update", "skill crystallization", "Thompson sampling", "monster-barring", "near-miss", "Kuhnian crisis", "post-execution learning". NOT for pre-execution risk scanning (use windags-premortem), retrospective analysis (use windags-looking-back), or DAG construction (use windags-architect).

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Load expert mental models on-demand to enhance reasoning, with a library of modules across 15 categories and commands to manage a personal crew.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution on local Docker, Slurm HPC, or cloud platforms.

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.

黑崎一护（少年漫）认知与表达框架（压缩蒸馏）：守护宣言、代打美学、成长型热血 触发：BLEACH 等。虚构；非暴力教唆

五条悟（少年漫）认知与表达框架（压缩蒸馏）：无敌教师、眼罩梗、领域展开爽点 触发：咒术回战 等。虚构；非暴力细节

Orquestrador do plugin civel (Civil Litigation Master) e porta unica do contencioso civel. Recebe qualquer demanda em linguagem natural, identifica a fase processual e o objetivo, e DIRIME (seleciona e conduz) TODAS as skills pertinentes sem esquecer nenhuma, fechando pela suprema-corte-civel. Use quando o operador descrever uma tarefa civel sem chamar skill especifica, ou disser civel-master, novo caso civel, vou ajuizar, fui citado, recebi sentenca, quero recorrer, preciso da inicial, contestacao, replica, tutela, agravo, apelacao.

NVIDIA NemoClaw plugin for secure sandboxed installation and orchestration of OpenClaw always-on AI assistants via OpenShell

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

莫言（作家）认知与表达框架（压缩蒸馏）：魔幻乡土、感官暴力与民间口语 触发：红高粱、诺奖演说 等。虚构；非煽动

绿谷出久（少年漫）认知与表达框架（压缩蒸馏）：无个性起点、笔记英雄学、哭腔热血 触发：我的英雄学院 等。虚构；非暴力教唆

Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes for model serving with GPU support.

Provides guidance for training Mixture-of-Experts models with long context windows, covering context parallelism sizing, selective recomputation, dispatcher choices, and practical patterns from recent experiments.

Provides storage and environment conventions for NeMo-RL agents on Brev instances, ensuring large experiment outputs go to /ephemeral and secrets are loaded from .env.

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.