Search

A collection of AI agent skills with interactive selection

Workbench for AI agent skills — init, lint, test, bench, and gate-checked install of standard SKILL.md skills

TypeScript SDK for Amp CLI - Build custom AI agents with Amp's capabilities

Duct SDK — manifest, CLI, and embed components for permissioned human and agent access to your product APIs.

Manage Kodara agent definitions as versioned Markdown folders.

Build an AI agent that competes on Arcade1v1 in a few lines: matchmake, play headlessly, sign and submit a replay-verified score — then read the rich result (PnL, ELO, the opponent's replay) and improve.

Batch-API-native coding agent: plan realtime, execute on 24h-SLA batch APIs, optimize like a query engine.

Agent-ready command-line interface for Drone CI (builds, logs, repos, secrets, crons, usage reporting). Installs the `drone-cli` command.

Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#task-spend) for that task based on aggregate spend, filtered by your...

Human-in-the-loop for the OpenAI Agents SDK: a function tool that asks a real human on their phone and blocks on a fail-closed answer.

Human-in-the-loop for CrewAI: a BaseTool that asks a real human on their phone and blocks on a fail-closed answer, instead of the console human_input prompt.

Human-in-the-loop for LangGraph and LangChain: a blocking ask_human, plus a durable interrupt()/Command resume that reaches your user on their phone.

Schema lockfile for LLM tool contracts

Core SDK for MKS Mission Control - Git + Taskwarrior CLI wrappers

Privacy-first AI Healthcare platform for HIPAA-compliant clinical workflows. Features a stateful LangGraph & MAF multi-agent RAG system, local Ollama LLMs, FastAPI, and React. Integrates PySpark Medallion Lakehouse analytics, HAPI FHIR patient imports, medical diagnostics ML models, and secure EHR hospital operations.

Kotlin-first framework for building Model Agnostic AI applications, RAG systems, and agentic workflows on Android and Kotlin Multiplatform.

A desktop control center for Eve agents — run, chat, build, wire, and deploy every Eve agent from one native app.

A persistent affect, memory & time engine for LLM companions — feelings that carry across sessions.

Calibrated accept / abstain-and-escalate decisions for agent tool calls, backed by split conformal prediction's finite-sample coverage guarantee.

Convergence debt and meridian docking protocols for multi-agent systems