Claw-Empire is a self-hosted AI agent manager that presents collaborative work as a pixel-art office. It's for developers and other people who want to delegate projects to several agents, assign department roles and review their output in one place. The office view shows agents working and meeting, while a Kanban board tracks tasks through completion.
It runs on macOS, Windows and Linux, with Docker deployment available. The project is open source under Apache 2.0. It stores application data in local SQLite, and encrypts OAuth and messenger credentials at rest. Model connections are separate: Ollama provides a local backend option, while external AI APIs send requests to their providers. Local application storage doesn't make cloud-backed agents offline.
Supported coding assistants include Claude Code, Codex CLI, Gemini CLI, OpenCode and Kimi Code. Agents can also connect through GitHub or Google OAuth and APIs such as OpenAI, Anthropic and OpenRouter. You can assign particular agents to projects and give them custom skills. For coding work, each agent uses an isolated Git worktree, with merges subject to your approval.
Workflows cover software development, reports, citation-focused web research, novels, video pre-production and roleplay. Each has its own department structure, review rules and output templates. Agents can hold meetings and produce minutes; the interface keeps completion reports and can export presentations to PowerPoint. Telegram, Discord, Slack and other messenger connections let you send directives and receive updates without requiring OpenClaw.
Claim this page and we'll verify you by hand. Claw-Empire gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Claw-Empire?Promote it
Something wrong or outdated on this page?
597Updated 14 hours agoMIT
Windows · Linux · Web#Agent Skills#Code execution#Git integration
Avibe gives Claude Code, Codex, and OpenCode a shared browser workspace while their processes run on your own machine. It's for people who want to manage coding agents, keep background work going, and review results away from their desk. The software is free and open source under the MIT license; you supply your own agent subscriptions or API keys.
18.2KUpdated 5 months agoApache-2.0
macOS · Windows · Linux · Docker · Web#Guardrails#Human approval#Knowledge graphs
34.4KUpdated 2 months agoApache-2.0
macOS · Windows · Linux · Docker · Web#Batch processing#Human approval#MCP
3.7KUpdated 2 days agoApache-2.0
iOS · Android · Docker · Web#Agent Client Protocol#Agent Skills#Code execution
1.4KUpdated 3 weeks agoMIT
Linux · Docker · Web#Agent Skills#Batch processing#Code execution
2.4KUpdated 1 week ago
Windows · Linux · iOS · Docker · Web#Code execution#Distributed execution#Git integration
AgentsMesh coordinates AI coding agents across your own machines for developers and teams managing concurrent work. Runners execute agents on local hardware or servers you control, while a shared console lets you assign tasks and follow progress. The paid hosted service provides the control platform; private deployments support Docker, Kubernetes, and air-gapped environments. You bring your own AI API keys, so model access depends on the agents and providers you use.
OpenFang runs scheduled AI agents on your own machine, with built-in task packages called Hands that report results to a dashboard. It's for people who want recurring research, monitoring or business tasks to continue without prompting an agent each time. The open source platform runs on macOS, Windows and Linux under the Apache 2.0 license.
ChatDev is a self-hosted platform for building teams of AI agents through a visual workflow editor. It's for people who want agents to collaborate on research, data analysis or software projects without writing the orchestration code themselves. You define each agent's role and how information passes between them.
Codeg is an open source AI coding workspace for developers who want Claude Code, Codex, Gemini and other agents working together on their own computer or server. It runs as a desktop app, a standalone server or a Docker container and uses the Apache 2.0 license.
AgentFlow is an MIT-licensed Python framework for developers who want several coding agents to share a workflow. It connects Codex, Claude, Kimi, and Pi tasks in dependency graphs, so planning can feed implementation and parallel reviews can feed a combined result. Agents can run in local Docker containers or on remote machines through SSH, EC2, and ECS.