Crates

Track Apple devices and AirTags via FindMy.app on macOS using AppleScript and screen capture.

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

Send and receive iMessages/SMS via the imsg CLI on macOS.

Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.

Read-only local archive and full-text search of WhatsApp Desktop messages via the wacrawl CLI. Use for searching chat history, exporting conversations, and creating encrypted backups. macOS only (reads local WhatsApp Desktop SQLite databases).

Add, remove, configure, and troubleshoot MCP (Model Context Protocol) servers. Use when the user wants to connect external tools, manage MCP server lifecycle, or debug MCP connectivity issues.

Sync and archive data from messaging platforms (WhatsApp, Discord, Slack, Twitter/X, Google) into Moltis memory as daily digest summaries. Orchestrates crawl tools and writes structured markdown to the memory system.

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

Generate professional infographics with 21 layout types and 21 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "visual summary", "信息图", "可视化", or "高密度信息大图".

Inspect and analyze codebases using pygount for LOC counting, language breakdown, and code-vs-comment ratios. Use when asked to check lines of code, repo size, language composition, or codebase stats.

54 production-quality design systems extracted from real websites. Load a template to generate HTML/CSS that matches the visual identity of sites like Stripe, Linear, Vercel, Notion, Airbnb, and more. Each template includes colors, typography, components, layout rules, and ready-to-use CSS values.

Create and manage webhook subscriptions for event-driven agent activation. Use when the user wants external services (GitHub, GitLab, Stripe, Linear, PagerDuty, Sentry, or any generic source) to trigger agent runs by POSTing events to a URL.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.