OpenFlowKit
Free, open-source diagrams you and your AI edit together
197 followers
Free, open-source diagrams you and your AI edit together
197 followers
A free, open-source diagram canvas: MIT, local-first, no account, in your browser. One canvas, five ways in. Draw it. Write it as code, or paste Mermaid, D2 or Structurizr. Ask any of 10 AI providers, or a local model. Hand it to your coding agent: Claude Code edits the canvas you have open, live, over MCP. Or pull it from a GitHub repo, every arrow citing its file and line. The CLI checks drift in CI, so diagrams keep up with your code.
This is the 2nd launch from OpenFlowKit. View more
OpenFlowKit 2
Launched this week
A free, open-source diagram canvas: MIT, local-first, no account, in your browser. One canvas, five ways in. Draw it. Write it as code, or paste Mermaid, D2 or Structurizr. Ask any of 10 AI providers, or a local model. Hand it to your coding agent: Claude Code edits the canvas you have open, live, over MCP. Or pull it from a GitHub repo, every arrow citing its file and line. The CLI checks drift in CI, so diagrams keep up with your code.
Free
Launch Team / Built With
The one I keep redrawing is which service is allowed to touch which table, and static imports is exactly where that one falls over. An import graph tells you what can call what, not what does, so the edges I care about are the ones that only exist at runtime, a queue, a webhook, a cron job hitting an endpoint nobody imports. Drift check will happily tell me the diagram is current while the edge that would actually hurt me was never on it. Worth saying you listed that limit yourself, most launches bury it.
@asadmalik901 Spot on, and that’s exactly the gap. Imports show what can talk, not what does. Queues, webhooks and cron edges are the ones I most want to get right next. Which would help you more: reading them from config (queue names, cron files, webhook routes), or a way to add them by hand so drift check guards them too?