Multi-agent workflows, orchestration frameworks, and autonomous runs.
Tools for running more than one agent, or one agent for longer than a single turn. This covers orchestration frameworks that split work across sub-agents, planning loops that decompose a task before executing it, handoff patterns, and harnesses that keep long autonomous runs from drifting. Useful when a job is too big for one prompt and you need structure rather than a bigger context window.
Ranked by GitHub stars. Search to find fast, or page through the full list.
Sanity plugin for Claude Code with MCP server, agent skills, agent rules, and slash commands.
Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI platform reads (Claude Code, Codex, Copilot, Cursor, Warp, OpenClaw, and 6 more) so one source of truth works across 10 platforms. Optional utilities for persistent artifact memory, background orchestration, autonomous loops, and artifact indexing.
End-to-end Agent Observability pipeline for an instrumented mlapp — classify production traces, root-cause failures, bootstrap evaluators, then (optionally) sample + publish a dataset, generate + run an experiment, and analyze results. Six narrated phases with a standardized banner and a "continue" checkpoint between each. Pure orchestration over the agent-observability sub-skills (agent-observability-session-classify, agent-observability-trace-rca, agent-observability-eval-bootstrap, agent-observability-experiment-py-bootstrap, agent-observability-experiment-analyzer). Use when user says "run the eval pipeline", "go from traces to evals", "bootstrap evals end to end", "classify then RCA then bootstrap", "build an eval set from scratch", "onboard me to datasets and experiments", "walk me through experiments", "I have an mlapp, now what", "Agent Observability onboarding", "guided experiment setup", "from traces to experiments", or wants a deterministic, narrated tour from production data through evaluators, datasets, and experiments. Stop early with --stop-after <phase> to short-circuit at evaluators or dataset, or resume mid-flow with --start-at <phase>.
Agent Skill for Baidu Netdisk (百度网盘) — upload, download, transfer, share, search files via natural language.
Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says "generate Python experiment", "write an SDK experiment", "create a ddtrace experiment", "Python notebook experiment", "use the Agent Observability SDK", or has ddtrace installed and wants idiomatic SDK code.
Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit Python SDK code or a framework-agnostic JSON spec instead. Use when user says "bootstrap evaluators", "generate evaluators", "create evals from traces", "eval bootstrap", "write evaluators", "build eval suite", "publish evaluators", or wants to generate BaseEvaluator/LLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.
Datadog skills for AI agents. Essential monitoring, logging, tracing and observability.
Use 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK
Agent skills for Meta Quest and Horizon OS development. Helps Claude assist with Quest app debugging, performance analysis, project setup, Unity and WebXR workflows, Spatial SDK and Platform SDK integration, store submission checks, and metavr device workflows.
An iterative implementation methodology that pairs with superpowers. Extracts requirements with proof obligations from large spec collateral, defines a walking skeleton that closes a real journey, then loops through audited sprints building a behavior evidence corpus until an auditor confirms the product matches the spec. Designed for comprehensive or ambiguous specs where the upfront writing-plans flow loses the plot.
Open Agent OS for Claude Code, Codex, and Cursor: meta-agent builder, A2A Hub routing, local ontology, memory/security gates.
Use when an agent folder must pass the Agentlas Cloud 2-stage security scan (static rules + BYOK LLM judgment) before private sync or public publish, or when asked to run/interpret hephaestus security scan.
Core planning and workflow infrastructure for the Claudikins ecosystem
Official agent skills for the Venice.ai API — private-by-default inference for chat, images, video, audio, embeddings, characters, billing, wallet (x402), and crypto RPC.
An MCP server that provides a tool to ask a user questions via the terminal
Generate FieldFlow servers that expose OpenAPI REST APIs as field-filtered tools for HTTP or MCP clients.
Join video meetings (Google Meet, Zoom, Teams) as an AI bot with voice, avatar, screenshare, and real-time transcription. Any AI agent can participate in calls via voice conversation, TTS, and meeting intelligence.
AI skills for Power Apps Canvas Apps - generate, modify, and integrate.
aai-gateway MCP server
Advanced web research and content discovery MCP server
AI-powered cascading development framework with design document system and multi-agent collaboration. Breaks down projects into Features (Mega Plan), Features into Stories (Hybrid Ralph), with auto-generated technical design docs, dependency-driven batch execution, Git Worktree isolation, and support for multiple AI agents (Codex, Amp, Aider, etc.).
Delegate coding, code review, analysis, and research jobs to Google Antigravity CLI (agy) sub-agents that run alongside your own work. Use this whenever the user asks to spin off, offload, or delegate a task to Antigravity, agy, Gemini, or an "external agent"; wants a second opinion or independent review from a different model; wants intensive repo work (audits, large refactors, research sweeps) run in the background while you keep working; or says things like "have Antigravity do it", "spin up a sub-agent for this", or "get more done in parallel". Also use it proactively when a task is a good fit for parallel delegation and the user has expressed a preference for using Antigravity workers.
Agent skills for AI coding agents working with Apollo GraphQL tools and technologies
Token-2022 extensions specialist for advanced token mechanics, token economics design, launch strategies, and liquidity management on Solana. Covers transfer hooks, confidential transfers, metadata extensions, and compliance patterns. Use when: Creating tokens with Token-2022 extensions, designing token economics, implementing transfer hooks or fees, setting up token launches, configuring metadata extensions, building compliance-ready token infrastructure, or minting NFTs/digital assets (Metaplex Core, Token Metadata, cNFTs, Candy Machine).
Find and validate what to build in crypto. Use when the user asks "what should I build", "validate this idea", "is this worth building", "find me a startup idea", "crypto idea", or wants blunt feedback on a project concept before writing code.
Cinema 4D MCP Server for Claude Desktop with MoGraph support
Bridge API service connecting Ollama with Model Context Protocol (MCP) servers
MCP server for delegating tasks to specialized AI assistants in Cursor and other tools
Claude Code plugin for CesiumJS domain skills and browser-based iteration via Chrome DevTools.
Core Solana dev kit: agents, workflow commands, go-to-market skills, MCP servers, and dev hooks. The full install (install.sh) additionally ships .claude/rules, the permissions/sandbox policy, and 18 ext/ submodules.
Unified skill hub for Solana development. Routes to external submodule skills (solana-foundation, sendai, solana-game, trailofbits, cloudflare, qedgen, colosseum, solana-new, ghostsecurity, defending-code) and local skills. Progressive disclosure — read only what you need.
Research sprint orchestrator for Claude Code. Structured research with claims, evidence tiers, and compiled output.
An agent-routed harness for end-to-end software product development
Launch agent teams for any kind of work — coding, writing, diagnosis, and more
Production-ready Claude Code skills, agents, and project templates for Craft CMS 5 development
model-compose: Declarative AI Workflow Orchestrator
Delegation system with workflow orchestration, specialized agents, and parallel execution for Claude Code
MCP server for Nutrient DWS Processor API
Drive the ServiceGraph API — metrics-enriched business datasets for founders (agencies, directories, newsletters, and more). Ships a branded servicegraph skill that works against any dataset, plus 14 specific skills for the US professional-services catalog (law, marketing, consulting, accounting, IT services, engineering, HR, PR, design, and more) and 3 product-directory skills for where to launch a software product and earn backlinks (general product/SaaS directories, MCP-server registries, and AI-tool/agent directories).
A personal assistant that lives in your project — memory-driven learning, daily rhythm, idle agency, and operational hygiene for Claude Code
MCP server for multi-round AI brainstorming debates across multiple models
Autonomous software development workflows with minimal token usage via on-demand resource loading
Transforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.
Designs and coordinates multi-agent pipelines where specialized agents collaborate to complete complex tasks. Includes communication protocols, failure handling, and state management.
Turn Claude Code into a persistent agent — memory, personality, voice, messaging, and more.
Multi-agent PR, CI, and downstream fork-sync review desk for Claude Code.
Plans and applies safe Kirby content migrations using runtime content tools, update schemas, and explicit confirmation. Use when users need to rename/move/transform fields, clean up content, or bulk-update pages/files across languages.
Improves IDE autocomplete and static analysis in Kirby projects with PHPDoc hints and Kirby IDE helper generation. Use when types are missing or IDE support is degraded.