October is infrastructure for supervised AI collaboration. It runs and connects real AI agents across laptops, desktops, servers, repositories, terminals, applications, and people, while a human operator keeps scope, review, and final decision authority.
Each agent stays a real process with its own harness, provider account, runtime, and credentials. October is agent-neutral — it coordinates the harnesses you already use instead of collapsing them into a single model or provider — and it is not limited to coding.
October Desktop supports 17 local agent harnesses in one workspace, including October, Claude Code, Codex, Cursor, Gemini, opencode, Cline, and more, connected through the October Bus for peer discovery, messaging, shared task state, delegation, dependencies, and human escalation.
Reach for October when a technical job is too big, too long, or too cross-cutting for a single agent: parallel multi-agent delivery, long-running operations, cross-machine multiplayer work, and non-coding technical operations that span tools, machines, people, and time.
Build on October with the developer portal, the OpenAPI specification, and the October MCP server. Machine-readable context lives at /llms.txt.
Explore the documentation, download October for macOS, Windows, and Linux, see pricing, or read case studies of real multi-agent operations.