> browse/registry

> peft-fine-tuning

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when a user asks to fine-tune a language model, train a custom LLM, adapt a model to their data, use LoRA or QLoRA, fine-tune Llama or Mistral, or train a model on consumer GPUs. Covers PEFT methods for 7B-70B parameter models.

> mintlify

Create beautiful developer documentation with Mintlify — AI-powered docs platform. Use when someone asks to "create documentation site", "Mintlify", "developer docs", "API documentation", "beautiful docs like Stripe", or "documentation platform with AI search". Covers page creation, API reference generation, components, analytics, and AI chat.

> openai-sdk

Integrate OpenAI APIs into applications. Use when a user asks to add GPT or ChatGPT to an app, generate text with OpenAI, build a chatbot, use GPT-4 or o1 models, generate embeddings, use function calling, stream chat completions, build AI features, moderate content, generate images with DALL-E, transcribe audio with Whisper API, or integrate any OpenAI model. Covers Chat Completions, Assistants API, function calling, embeddings, streaming, vision, DALL-E, Whisper, and moderation.

> mlflow

Open-source platform for managing the ML lifecycle. Track experiments with metrics and parameters, register and version models, deploy models to various targets, and build reproducible ML pipelines. Integrates with all major ML frameworks.

> openai-agents

You are an expert in the OpenAI Agents SDK (formerly Swarm), the official framework for building multi-agent systems. You help developers create agents with tool calling, guardrails, agent handoffs, streaming, tracing, and MCP integration — building production-grade AI agents that coordinate, delegate tasks, and execute tools with built-in safety controls.

> openai-codex-cli

You are an expert in OpenAI's Codex CLI, the open-source terminal-based coding agent that reads your codebase, generates and edits code, runs shell commands, and applies changes — all within your terminal. You help developers use Codex CLI for code generation, refactoring, debugging, and automation with configurable approval modes (suggest, auto-edit, full-auto) and sandboxed execution for safety.

> openai-realtime

Build voice-enabled AI applications with the OpenAI Realtime API. Use when a user asks to implement real-time voice conversations, stream audio with WebSockets, build voice assistants, or integrate OpenAI audio capabilities.

> openclaw

Deploy and manage OpenClaw, a self-hosted gateway bridging messaging platforms to AI coding agents. Use when a user asks to set up OpenClaw, connect WhatsApp or Telegram or Discord to an AI agent, configure multi-agent routing, schedule cron jobs in OpenClaw, set up webhooks, manage OpenClaw channels, pair a messaging account, configure heartbeats, spawn sub-agents, or troubleshoot OpenClaw gateway issues. Covers installation, channel setup, agent configuration, cron scheduling, webhooks, and su

> streamlit

Expert guidance for Streamlit, the Python framework for building interactive data applications and dashboards. Helps developers create web apps for data exploration, ML model demos, and internal tools using pure Python — no frontend skills required.

> modal

Serverless GPU compute platform for running Python functions in the cloud. Deploy ML models, run training jobs, and serve inference endpoints without managing infrastructure. Supports A100/H100 GPUs, custom container images, and scales to zero automatically.

> mongodb

Assists with designing document schemas, building aggregation pipelines, managing indexes, and operating MongoDB clusters. Use when working with flexible schemas, nested documents, horizontal scaling, Atlas Search, or vector search for AI applications. Trigger words: mongodb, mongo, document database, aggregation, atlas, nosql.

> litellm

Call 100+ LLM APIs with one interface using LiteLLM — unified API proxy for OpenAI, Anthropic, Google, Mistral, Cohere, and self-hosted models. Use when someone asks to "switch between LLM providers", "LiteLLM", "unified LLM API", "LLM proxy", "call Claude and GPT with the same code", "LLM load balancing", or "multi-model AI gateway". Covers provider routing, fallbacks, rate limiting, spend tracking, and self-hosted proxy.

> kaboom

You are an expert in Kaboom.js (now maintained as Kaplay), the beginner-friendly game library for making browser games quickly. You help developers build games using Kaboom's component-based entity system, built-in physics, sprite loading, scene management, and event system — where games can be built in under 100 lines of code while still supporting complex gameplay through composable components.

> kaggle-finetune

End-to-end workflow for fine-tuning LLMs using Kaggle datasets. Use when downloading datasets from Kaggle for model training, preparing conversation/customer service data for chatbot fine-tuning, or building domain-specific AI assistants. Covers dataset discovery, download, preprocessing into chat format, and integration with PEFT/LoRA training.

> koa

You are an expert in Koa, the minimalist web framework created by the Express team. You help developers build APIs and web services using Koa's async/await middleware stack, context object, and composable architecture — providing a lightweight foundation where you add only what you need through middleware, without bundled routing or templating.

> label-studio

Open-source data labeling and annotation platform for ML projects. Supports text, image, audio, video, and time-series data. Features configurable labeling interfaces, ML-assisted labeling, team collaboration, and API integration for automated workflows.

> lancedb

Embedded vector database with LanceDB — serverless, zero-config vector search for AI applications. Use when someone asks to "vector search without a server", "embedded vector database", "LanceDB", "local vector search", "serverless vector DB", "vector search in a file", or "lightweight RAG storage". Covers table creation, vector search, full-text search, hybrid search, and multimodal embeddings.

> langfuse

You are an expert in Langfuse, the open-source LLM engineering platform. You help developers trace LLM calls, evaluate output quality, manage prompts, track costs and latency, run experiments, and build evaluation datasets — providing full observability into AI applications from development through production.

> langgraph

Build stateful, multi-step AI agents and workflows with LangGraph. Use when a user asks to create AI agents with complex logic, build multi-agent systems, implement human-in-the-loop workflows, create state machines for LLMs, build agentic RAG, implement tool-calling agents with branching logic, create planning agents, build supervisor/worker patterns, or orchestrate multi-step AI pipelines with cycles, persistence, and streaming.

> langsmith

Monitor, trace, debug, and evaluate LLM applications with LangSmith. Use when a user asks to trace LLM calls, debug chain executions, evaluate AI output quality, set up LLM observability, monitor agent performance, run prompt experiments, compare model outputs, create evaluation datasets, track token usage and latency, or build LLM testing pipelines. Covers tracing, datasets, evaluators, annotation queues, prompt hub, and production monitoring.