AI agent workspace / orchestration
Self-hosted platform that lets users create, manage, and run AI agents across devices, with workspaces and a task board accessible from desktop, mobile, browser, or API.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose it for a lighter, terminal-native runtime with a combined GUI+TUI, if you prefer a single local binary over a web-based workspace with mobile/API access.
Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.
Choose it if you need an enterprise-grade agentic workspace with 100+ integrations and shared memory.
Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose it if you need to schedule and supervise a fleet of agents in an organization, with 24/7 operations.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose it if you only manage coding agents (Claude Code etc.) and want a desktop app with Git worktrees and code diffs.
Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Feishu, DingTalk, Telegram, WhatsApp and H5 access.
Choose it if you need to run 100+ coding agents in parallel inside an IDE-like environment.
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
Choose it if you want a visual canvas to edit outputs of multiple coding agents in markdown/diagrams.
Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks. Free, MIT-licensed desktop app for macOS, Windows, Linux, with mobile companion for iOS and Android.
Choose it if you want an agentic development environment specifically for running many coding agents with your own subscriptions.
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.
Choose it if you want a simple cross-device orchestrator specifically for coding agents.
Orchestrate multiple coding agents from desktop and mobile
Choose it if you want an agent IDE that autonomously handles CI fixes and code review for coding agents.
Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.
Choose it if you are a developer who wants to swap between coding agent harnesses behind a policy-controlled API.
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
Choose it if you prefer a lightweight CLI for managing multiple terminal coding agents.
Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.
Choose it if you want an open-source agentic IDE to run multiple coding agents from any provider.
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
Choose it if you need a local-first workbench tailored to Codex/DeepSeek/OpenCode harnesses with unified skills.
Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.
Choose it if you want a visible CLI to mix and manage many different coding agents.
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents
These projects were analysed and named yao among their alternatives. The relationship is not symmetric — how yao rates them is a separate judgement, made when yao is analysed in its own right.
calls yao “Choose when you want a self-hosted board-style task tracker for agents across devices.”
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
calls yao “choose it when you want a device-agnostic hub to manage agents and track tasks on a board.”
Self-hosted AI workspace.
calls yao “Choose over Khoj if you want a self-hosted agent/task workspace with a board UI and API, and don't need deep personal-document RAG.”
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
calls yao “Use when you want a self-hosted agent/workspace manager with task boards across desktop, mobile, browser, and API.”
Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.
calls yao “Use when you want a self-hosted, board-based view of agents and workspaces across devices.”
Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.
calls yao “Pick it for a self-hosted task-board workspace for agents across desktop, mobile, browser, and API.”
A multi-model AI agent desktop client — connect any AI provider, extend with MCP & skills, control from your phone. Built with Electron + Next.js.
calls yao “Choose it for a self-hosted agent platform with a task board and API when you need cross-device tracking.”
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
calls yao “Go self-hosted platform if you want agents, boards and devices exposed through APIs/low-code rather than a coding-only tool.”
Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-hosted server, or Docker.