Open source feature flags. Every flag is a markdown file that lives with the code it controls: what it does, why it exists, and what you decided, reviewed in a PR like any other change. Your coding agent installs Dif in one command, no account, and reads the context file so it knows what's live and what was already tried. A/B tests wait in the same files until you have traffic. Send events to your own analytics, or let Dif Cloud read the results and write the decision into the file.
Forum Threads
Recent product updates & and an ask for help! -- yours truly @ dif team
Let's get to the exciting part first. Here are some recent product updates that help your coding agents work even more seamlessly with dif.sh. Get to it! it's time to learn and keep good product growth principles alive.
Vercel Flags SDK adapter. @dif.sh/flags-sdk is now on npm. Users get the same variant whether they come through dif(), React, Svelte, OpenFeature or the Flags SDK. The JS OpenFeature server provider now publishes with each release, and we ve submitted dif to the OpenFeature ecosystem page.
Better tooling for coding agents. v0.7.0 adds a triage skill that checks your running experiments, a conclude skill that reads results from dif Cloud, a Cursor rule and a Claude Code plugin. dif init --agents-only updates the agent files without changing anything else.
GitHub Action. dif-action v1 builds and validates your experiment spec in CI.
Starter repos for the Next.js App Router and SvelteKit, each set up with one flag.
dif Cloud. A verdict engine that makes ship/kill calls and checks guardrail metrics, a read-only API with OpenAPI docs and read tokens, and an MCP server with OAuth so agents can ask for experiment results directly.
Here is the part that feels a little uneasy. Asking for help is hard... but it takes @product Community to build a product. So I'll keep this brief.
Give us a star on Github! https://github.com/dif-sh/dif
It takes a second and helps us a lot.
TY
dif.sh update: the agent layer, explained properly this time
We launched dif on Sep 5 and the most-asked question in the comments was some version of what does the agent part actually do? So here is a bit more context:
dif init writes a managed block into AGENTS.md, CLAUDE.md, and .cursorrules. The block tells the agent where flag files live, the frontmatter schema, the dif("flag-id") call at the render site, and to run dif validate before opening a PR. It also installs three Claude Code skills into .claude/skills/: one proposes the surfaces in your app, one drafts a flag or test, one concludes it and writes the learning back to the repo.
Every dif build refreshes dif/context.json, so the next session starts knowing what is live and what already got killed.
Pick what you want with --agents claude, --agents cursor, --agents general, or --agents none.
🎉 A huge thank you from the dif.sh team!
To everybody that made our product hunt launch a success! We are proud to have been voted "Product of the day"!We appreciate the enthusiasm and excitement around dif.sh.
As always, please continue to share your feedback. We have so many more ideas in the pipeline and can't wait to show them to you.
best, David
Congrats on the launch. The "flags reviewed in a PR" part is the real hook for me - most flag tools bolt on a dashboard that nobody checks, and this just stays in the same review flow. Curious about one thing though: if two agents are working in parallel branches and both touch the same markdown flag file, does dif help resolve that conflict at all or is it just a normal git merge conflict at that point?
@galdayan Right now it's just a normal git merge. That's a good idea to add though, we'll note it!