All activity
Shashi Sharmaleft a comment
Super impressive how far this has evolved — especially the shift from pure observability to a full LLM engineering platform. One thing I keep running into though: even with great tracing and evals, debugging still breaks down when you try to reproduce issues locally — especially with non-deterministic behavior (tool calls, async chains, external APIs, etc). Feels like we’ve solved “what...
Langfuse 2.0the open source LLM engineering platform
Flux records API executions so you can replay failures locally, fix them, and resume execution safely.
Instead of guessing from logs, you get the exact request, inputs, and behavior.
Same request. Same IO. Same outcome.
FluxFix production bugs by replaying them locally
Shashi Sharmaleft a comment
Hey everyone 👋 I built Flux because debugging production bugs always felt like guesswork. You look at logs, try to reproduce locally, add more logs, redeploy… and repeat. Flux changes that. It records every request (including external calls), so you can replay the exact failure locally. Fix the bug → replay safely → then resume the same execution with real IO. No mocks. No staging. No duplicate...
FluxFix production bugs by replaying them locally