multi-agent AI coding workspace / agentic development environment (ADE)
Codeg is a multi-agent AI coding workspace that aggregates sessions from many agent CLIs (Claude Code, Codex, OpenCode, Pi, Grok Build, etc.) into one searchable desktop app / self-hosted server / Docker deployment with sub-agent delegation and a branch-per-task board.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Pick it if you want a TypeScript/web-stack ADE with a 100+ agent catalog and bring-your-own-subscription auth instead of Codeg's Rust desktop+server split.
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
Choose it when you need Go, Apache-2.0 team-level governance covering planning through merge plus cloud/mobile runners.
Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.
Apache-2.0 TypeScript ADE if you prefer an Electron-style stack and provider-agnostic parallelism without Codeg's ACP registration flow.
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
Take it over Codeg when per-agent isolated sandboxes matter more than cross-agent collaboration, accepting AGPL-3.0.
A desktop app for isolated, parallel agentic development
Rust/Apache-2.0 option if you want a shared blackboard model for agents rather than session aggregation.
🏄🏼♂️ The blackboard for coding agents - agentic development environment for claude code, codex, cursor, opencode, grok and more.
MIT TypeScript ADE with desktop, mobile and remote runtime if you want that ecosystem and don't need Codeg's Docker self-hosting.
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.
Pick it when orchestration is mostly remote control of agents from desktop/mobile and you don't need a searchable session store.
Orchestrate multiple coding agents from desktop and mobile
Use it for a command-center view of parallel agents if you accept AGPL-3.0 copyleft.
Agent Orchestration Command Center
Kanban-first team model where agents message and review each other, if you want to steer only at a high level.
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/GitHub Copilot/Kiro/Z.AI/MiniMax/Kimi(200+ models, 75+ LLM providers, free models no auth). Build your AI company with multiple teams
MIT desktop workspace with worktrees, skills and WeChat/Feishu hooks if you need Chinese messaging integrations.
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.
MIT visual workspace if you want to edit agent output in markdown, diagrams and mockups rather than a plain diff view.
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.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Swift/MIT TUI-first runtime for developers who refuse to leave the terminal and skip a desktop/web layer entirely.
A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Coding Agent, Tmux alternative
Choose it when durable shared specs for agents matter more than running many agents in parallel at once.
ADE( Agentic Development Environment) The spec-driven environment for AI coding agents, where your planning becomes lasting, shared project context.
Bring-your-own-LLM parallel dev environment if you want raw model access rather than wrapping existing agent CLIs.
DevSwarm is an AI Development Environment (ADE) for parallel coding with multiple AI assistants. Bring your own LLM. Move fast while building right.
Python framework/meta-harness when you need to embed agent orchestration, policy and sandboxing in your own code, not consume an app.
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.
Visible CLI multiplexer for mixing several agent harnesses if you want no GUI or server installed at all.
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents
MIT Rust TUI/web manager when browser-based mobile access beats a native desktop shell.
Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding.
Minimal Go terminal-agent manager for CLI-only workflows where tmux-level footprint is preferred over a workspace app.
Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.
IDE-centric take on agent orchestration if you want to stay in the editor rather than a session/branch workspace.
The agent IDE that builds itself
Lightweight Tauri client when you only need one window over several agent engines, without server/mobile or sub-agent delegation.
Multi-engine AI coding desktop client (Tauri). Claude Code, Codex, Gemini, OpenCode, DeepSeek Harness and more in one GUI.
Elixir autonomous-run model for teams that hand off whole work items instead of driving a live interactive workspace.
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
Enterprise workspace with 100+ business integrations when your agents must reach systems beyond coding sessions.
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.
Go self-hosted platform if you want agents, boards and devices exposed through APIs/low-code rather than a coding-only tool.
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
Local-first single runtime for GUI and TUI when your agents span writing, design and research, not just code.
Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.
These projects were analysed and named codeg among their alternatives. The relationship is not symmetric — how codeg rates them is a separate judgement, made when codeg is analysed in its own right.
calls codeg “Choose it if you want a self-hosted, Docker-deployable multi-agent workspace with a Rust backend.”
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.
calls codeg “Rust-native collaborative workspace aggregating sessions from many agent CLIs; choose when you need Docker/self-hosted server deployment.”
Orchestrate multiple coding agents from desktop and mobile
calls codeg “choose for a Rust-based self-hosted collaborative workspace with Docker deployment.”
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
calls codeg “Use when you want a collaborative desktop/server/Docker workspace aggregating sessions from many existing agent CLIs.”
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 codeg “Choose it when you want a Rust multi-agent workspace that also runs self-hosted via server or Docker.”
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
calls codeg “choose over seed for a desktop/server workspace that aggregates sessions from multiple coding agents.”
Get 10X more out of Claude Code, Codex or any coding agent
calls codeg “choose when you want desktop/self-hosted/Docker aggregation of coding-agent sessions instead of a terminal app.”
Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.
calls codeg “Rust with a self-hosted server/Docker target and cross-CLI session aggregation, but thinner spend and run analytics.”
Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.
calls codeg “Choose it for a self-hosted or Docker multi-agent workspace that aggregates sessions from many CLI agents if you need collaborative server deployment over a macOS terminal app.”
A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Coding Agent, Tmux alternative
calls codeg “Choose it for a self-hosted multi-agent workspace aggregating many CLI sessions when you don't need Frame's spec-driven context.”
ADE( Agentic Development Environment) The spec-driven environment for AI coding agents, where your planning becomes lasting, shared project context.