Results for “macho”

Track and visualize ML training experiments with Trackio, including logging metrics, firing alerts, and retrieving data via CLI. Supports real-time dashboards, webhook alerts, and HF Space syncing.

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

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.

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

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

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, supporting text, image, video, and audio with fuzzy deduplication, quality filtering, semantic deduplication, PII redaction, and NSFW detection.

Use when voice AI strategy, conversational AI architecture, voice technology innovation, or voice platform leadership is needed. This agent specializes in voice AI leadership within the VoiceForge AI ecosystem.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace, covering architectures, routing, load balancing, and expert parallelism.

Official Puppeteer Model Context Protocol Server for browser automation.

Use when an agent needs to publish one simplebuzz post to MetaWeb (optionally with uploaded attachments); do not use this skill for private chat, service-order delegation, or network source management.

Drive Palmier Pro, an open source AI-native macOS video editor (Swift, SwiftUI/AppKit, AVFoundation) that exposes its timeline as an MCP server at `http://127.0.0.1:19789/mcp` so Claude Code/Desktop, Cursor, or Codex can read and edit a project's tracks, clips, media, transcript, captions, color/effects, and trigger generative AI (video/image/audio) requests side-by-side with a human editor. Use when the user wants to connect an agent to Palmier Pro's MCP server, call its timeline/clip/media/generation tools (`get_timeline`, `add_clips`, `move_clips`, `generate_video`, ...), build/run/test the Swift app from source, or debug the MCP tool surface in `ToolDefinitions.swift`/`ToolExecutor+*.swift`. Triggers on: "palmier pro", "palmier-pro", "AI video editor MCP", "connect Claude to my video editor", "palmier MCP server", "edit my timeline with an agent", "swift build PalmierPro", "palmier-pro mcpb", "manage_project"/"get_timeline"/"add_clips" tool.

Build and sharpen a project's domain model — a CONTEXT.md glossary and ubiquitous language. Use when pinning down terminology, or the agent "uses the wrong words". Repo decision-memory system (INDEX.md, rejected alternatives) → docs-adr.

Expert en service mesh (Istio, Linkerd, mTLS, traffic management, observabilité, contexte DZ)

Build AI agents, multi-agent teams, and agentic workflows using the Agno framework, with reference files covering agents, teams, workflows, memory, knowledge, and deployment.

Use when moc expertise is needed to unblock implementation decisions.

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.

Hand off the current task to another agent with full context. Use when the user says "handoff", "hand off", "hand this to", or wants to pass work to another agent (Codex or Claude).

Provides PhD-level mathematical analysis for machine learning, including optimization theory, statistical learning theory, and convergence proofs.

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.