OpenFlow is a visual builder for multi-agent AI workflows. You drag role cards onto a canvas, wire a pipeline such as planner, architect and coder, save it, and run it with real parallel agents. It is built on and shipped as a fork of opencode, whose headless server drives execution.
Be the first to rate OpenFlow. Your feedback helps other users decide.
Lay out role cards and wire them together instead of editing configuration files by hand.
Execute a planner, an architect and a coder at the same time rather than in sequence.
Save a pipeline and run it again on the next project.
Similar tools in the same category — compare side-by-side
DocuMemory is a memory engine that passively distils raw AI chat sessions into permanent architectur...
Nobodywho runs AI on your own devices and servers. Its open-source inference engine ships SDKs for R...
Ollaya downloads and serves open decision models on your own machine. You ask typed questions about ...
Guides and comparisons about code tools
Nine Show HN launches sitting under the agent: a model gateway, vectorless retrieval, on-device inference, an MCP browser layer and connectors for real systems.
Nine tools for supervising coding agents: phone alerts when an agent blocks, review inboxes, menu-bar contacts, shared scratchpads and team boards.
Nine tools that constrain what an agent can produce and reach: slop-detecting lint rules, declared sandbox tiers, cheaper crawling and signed messaging.
Twenty-five coding tools sorted by what they do: autocomplete, codebase comprehension, testing, or self-hostable models, from CodeGeeX to Codestral.
Coding agents increased output but not shipped software. The gap is verification, context and drift. Here is what converts agent output into working systems.
