Spotify's vendor-neutral workspace for running dozens of Claude Code, Codex and Gemini CLI sessions in parallel with shared context.
Multi-agent
Several specialised agents working together under an orchestrator, each owning part of the job.
31 apps, 3 skills and 1 MCP server tagged Multi-agent.
Apps
Meta's terminal coding agent for long-horizon work in large repositories, running the Muse Spark 1.2 model with parallel subagents and a replayable event log.
Open-source desktop AI agent that builds a local, readable memory of your work, then orchestrates agent fleets and durable workflows on top of it.
A single platform for building internal AI agents and multi-step agent systems, with memory, sandboxed compute, durable workflows, human approvals and 1,000+ integrations.
Block's open-source desktop workspace for AI agents — one native app for Goose, Claude Code, Codex, Copilot, Amp and Cursor.
Tencent Cloud's open-source, self-hosted AI assistant for households and small teams, with per-user expert agents, chat-app channels, connectors and remote desktop.
Open-source, self-hostable AI teammates with their own memory, routines, apps and computer, on any model you bring; also offered as a hosted service.
Open-source chat app for a team of AI bots that run on the Claude, Codex or Grok CLI you already have, each with its own model, computer and connected apps.
Free, local-first desktop app that runs Codex, Claude Code, Grok, Gemini and other agents as a persistent team with their own workspaces, queues and shared channels.
Open-source, self-hosted control plane that runs teams of AI agents like a company, with org charts, tasks, budgets and approvals.
A research community where independent AI agents discuss open problems and publish reviewed papers.
An agent-native cloud computer that pairs 20+ frontier models with skills, connectors, email and scheduled automations in one sandbox.
Multi-agent workspace where teams hire reusable "digital employees" — an orchestrator runs specialists in parallel and returns finished decks, dashboards, reports and Excel files.
A shared channel workspace where people and AI agents run recurring business work together — with goals, approvals and handoffs that survive a pause.
A marketplace of ready-to-run AI apps, agents and workflows — copy someone else's setup, run it as an app, publish your own and earn when it runs.
A governed platform for running AI agents in production, with Omni — an automated forward-deployed engineer that builds and maintains them for you.
An AI software factory: an orchestration layer that coordinates AI agents, tools and engineering workflows to carry tickets from requirement to reviewed pull request.
MIT-licensed multi-agent harness that turns the CLI coding agent you already use into a persistent clone of yourself, running around the clock.
An approval-first agent workspace for solo founders: planning, research, social and coding agents propose one next move at a time and only act once you say yes.
AI investment agents that research markets, monitor portfolios and place orders on your instruction, with every action logged for review.
Alibaba's agentic coding platform — a desktop IDE where a lead agent dispatches specialist sub-agents, backed by an auto-generated wiki of your repository.
A browser canvas where Claude Code, Codex, Kimi and other coding agents work the same repository at once without overwriting each other.
Open-source AI workspace where teams build, deploy and monitor agents on one canvas — visually or in code, across 1,000+ integrations.
The multi-agent framework where agents have roles and collaborate as a crew — plus a platform to run them in production.
Build a team of specialist AI agents — recruit, brief, and manage them like staff, with no code required.
Agent-native software development: Droids that plan, code, review, and ship across your existing toolchain.
Google's agent-first development platform, where you manage a fleet of coding agents across editor, terminal, and browser.
AI orchestrator agent for e-commerce — states a goal, dispatches specialist sub-agents, and returns finished work for approval.
An AI coworker that lives in your Slack — one teammate per channel, each with its own memory, tools, and approval rules.
AI agent platform where a coordinator called Otto runs AI "Experts" and scheduled workflows, available in the cloud or self-hosted.
Devin Desktop (formerly Windsurf) is Cognition's AI IDE for running and reviewing local and cloud coding agents.
Skills
Build crash-safe AI agents on AgentKit and step.ai — durable tool calls, human-in-the-loop approval, realtime progress, and when not to reach for an agent loop at all.
Google's skill for writing agent code with the Agent Development Kit (ADK) in Python or Go: agent types, tools, callbacks, state, multi-agent orchestration, the graph Workflow API and a catalogue of reference recipes, used with agents-cli.
Skill: VoltAgent Best Practices
by VoltAgent
VoltAgent's official conventions skill — when to reach for an agent versus a workflow, the expected project layout, and the core snippets for agents, workflows, memory and servers.
MCP servers
Local-first MCP server that lets Claude Code, Codex, Cursor, Gemini CLI and other coding agents message each other, claim files and hand off tasks in one repo.
Related tags
Tags that appear alongside this one, ranked by how often.