dify
https://github.com/langgenius/dify
TypeScript
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
TypeScript not yet supported3 Subscribers
Add a CodeTriage badge to dify
Help out
- Issues
- Automatic metadata filter crashes for time-typed fields (LLM returns date string instead of Unix timestamp)
- [Bug] Agent file upload: custom file types conflict with document/image types in v1.17
- The streaming output is lagging, with data being sent in chunks
- fix(web): ensure workflow canvas background does not overlay studio panels (#41451)
- fix(web): use DropdownMenuItem in dataset template card actions for complete menu a11y
- fix(mcp): keep session alive for orphaned responses
- fix(api): make Stop button actually cancel the upstream LLM stream
- fix(i18n): complete Turkish agent skills translations
- Langfuse v4 events_only mode silently drops all Dify traces (legacy ingestion API)
- feat(trace): migrate langfuse provider to v4 OTel-native ingestion
- Docs
- TypeScript not yet supported