Today we're releasing Critic, a platform to review the code your agents write. Try it out at critic.run

Since agents started writing our code, it has become harder to understand the scope of a change. Your AI has all the context behind the code but you don't.
explain what changed and why, and answer questions from anyone reviewing its work.

Security is a big focus for Critic. All prompts sent by critic run in a forked thread with read-only tools. That way, a Critic initiated prompt can only answer questions about the change at hand, and nothing else.

Critic is in early beta. Sign up for free at critic.run

Introducing MultiMatte, a background removal model you can aim with words. Name an object in your image, MultiMatte keeps just that thing and cuts the rest.

Same photo, three prompts: the dog, the dog bowl, the jeans.

Try it out: usefeyn.com/multimatte

MultiMatte is built on Meta's SAM 3. Our biggest win came from converting binary masks that classify each pixel as being inside or outside an object, to alpha mattes that assign an opacity value to every pixel. This allows MultiMatte to better understand hair, motion blur, boundaries.

Across all our measured benchmarks, MultiMatte shows a step improvement over SAM 3. On DIS5K, S-measure rises from 0.674 to 0.908 (a 34.6% relative gain), and on DUT-OMRON from 0.792 to 0.901 (13.7%).

Read more about MultiMatte x.com/status/2097797… or build with it using NoBg.

MultiMatte is open source. Check it out on HuggingFace: hf.co/feyninc/multim…

This could be you usefeyn.com/interest/

The assistant that gets you, powered by Feyn

Building FeyNoBg also exposed a tooling problem. Image matting models usually live in isolated repos with different interfaces.

So we built NoBg, a Python library for running, training models, and evaluating image mating models. Currently, it supports BiRefNet with more architectures coming. We hope you use it to build something exciting.

github.com/feyninc/nobg

We’re releasing FeyNoBg, our open-source model for image background removal.

Across eight benchmarks, it sets the best published S-measure on four and comes within 2% of the leader on the rest.

Try it out: huggingface.co/spaces/feyninc…

Building FeyNoBg also exposed a tooling problem. Image matting models usually live in isolated repos with different interfaces.

So we built NoBg, a Python library for running, training models, and evaluating image mating models. Currently, it supports BiRefNet with more architectures coming. We hope you use it to build something exciting.

github.com/feyninc/nobg

FeyNoBg and NoBg are both open source.

- Model: huggingface.co/feyninc/FeyNobg
- Try it: huggingface.co/spaces/feyninc…
- NoBg Library: github.com/feyninc/nobg
- Technical Blog: usefeyn.com/blog/feynobg/

We’re introducing SQRL, a family of small text-to-SQL models.

On the BIRD Dev benchmark, SQRL's 35B, 9B, and 4B models beat Claude Opus on SQL execution accuracy.

SQRL is open source and available on Hugging Face. The 9B model is our recommended default.

huggingface.co/feyninc

To develop SQRL, we first trained SQRL-35B-A3B as the teacher, then distilled its successful inspection trajectories into smaller 4B and 9B models.

Read more about how we developed SQRL: x.com/FeynAI/status/…