Runs Google Antigravity agents via the official agy CLI and configures Google Antigravity and Gemini CLI as MCP hosts; can also read Antigravity conversation history on a best-effort basis.
Runs local-model agents against Ollama's OpenAI-compatible /v1/chat/completions endpoint; currently chat-only with no file tools.
Runs Codex agents through OpenAI's official codex app-server JSON-RPC, configures ChatGPT desktop/Codex CLI, and can read Codex conversation history. Also supports OpenAI-compatible chat-completions backends.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@agent-fleet-mcp spawn a codex manager to refactor my auth module, then fetch its files"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that lets a lead agent (you in Claude Desktop, ChatGPT, Antigravity, Claude Code, VS Code, ...) run manager agents, and lets managers run their own child agents — across:
Backend | How it is driven | Needs |
| OpenAI's official |
|
| official | Antigravity CLI ( |
|
| Claude Code CLI, signed in |
|
| server running locally |
Agents created through Codex show up in the ChatGPT desktop app's Codex history, and Antigravity agents in Antigravity's history.
Needs Python 3.11+ and uv (or pip).
uv tool install git+https://github.com/s0wingseason/agent-fleet-mcp
agent-fleet install # adds agent-fleet to every supported app it finds
agent-fleet doctor # shows which apps and backends were foundThen fully quit and reopen each app (Claude Desktop and ChatGPT keep running in the tray).
agent-fleet install --hosts claude-desktop,codex limits it to some apps; --dry-run shows what would change. agent-fleet uninstall removes it again. Every edited config file gets a one-time *.agent-fleet.bak backup.
Apps it configures: Claude Desktop (including the Microsoft Store build), Claude Code, ChatGPT desktop / Codex CLI (~/.codex/config.toml), Google Antigravity (~/.gemini/.../mcp_config.json), Gemini CLI, VS Code, Cursor, Windsurf, LM Studio, Hermes Agent.
Not MCP hosts, so nothing is installed into them: Ollama, vLLM (use them as agent backends). Bionic and Open WebUI need manual setup (not covered yet).
Related MCP server: DZ23 Subagents Universal MCP
Tool | Who |
| everyone |
| lead: any agent; manager: its own children |
| same; files go through each agent's |
| lead only — reads Codex, Claude Code and Antigravity history saved on this PC, or takes over one of those conversations |
Typical lead prompt: "Use agent-fleet: spawn a codex manager to refactor X, an antigravity manager to write tests, wait for both, then fetch their files."
Calls never block more than ~55 s (MCP hosts time out around 60 s); poll wait_for_agents for long jobs.
Every app launches its own agent-fleet serve process. Agents run inside the process that created them; all processes share one SQLite database in ~/.agent-fleet, so every app sees every agent, its status and transcript. An agent can only be messaged from the app that runs it — unless that app has closed, in which case the next app to message it takes it over and resumes the same conversation.
Managers get the agent-fleet tools injected (Codex via -c mcp_servers..., Claude Code via --mcp-config) with their own identity; children run without them.
Folders: ~/.agent-fleet/agents/<id>/{work,inbox,outbox}, shared drop folder ~/.agent-fleet/exchange. Config: ~/.agent-fleet/config.toml (models, sandbox modes, limits, allowed folders).
Not yet tested end to end on Windows with all backends together; please file issues.
No Windows .exe installer yet (planned), and no desktop/UI automation.
Regular ChatGPT chats (not Codex) live in OpenAI's cloud and aren't readable here. Automating the ChatGPT window to scrape replies conflicts with OpenAI's Terms of Use; this project only uses OpenAI's own codex app-server interface.
Antigravity history reading is best-effort (undocumented storage format).
Local-model agents are chat-only (no file tools yet).
If codex on your PATH is a different program (e.g. the PyPI "codex" comic server), agent-fleet ignores it and looks for OpenAI's CLI under npm's global folder; agent-fleet doctor reports this.
Agents run with your user account. Codex agents default to workspace-write sandbox; Claude Code agents to acceptEdits; Antigravity agents to --sandbox. File tools refuse paths outside allowed folders and anything that looks like keys or credentials. Review ~/.agent-fleet/config.toml before giving agents broader access.
MIT licensed.
This server cannot be deployed
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Shared memory and mail for your AI agents. Verified with Claude Code; other MCP clients in testing.
Hosted MCP server and Agent Skills for specs, engineering threads, and project memory.