AI Attributes™
OpenEmotions™
LiveOpen models for emotions in text: the 28 GoEmotions labels.
Live. Try it and the API answer with the RoBERTa model; the Gemma model isn't served yet.
Open models for observing AI.
AI Attributes™ curates and develops open models that read attributes of text: emotions, moral framing and sensations today, more to come. Open weights on Hugging Face, and an API any platform can connect to.
Observersopen models that read text
OpenSensations™
PreviewOpen models for the senses in text: vision, hearing, smell, taste, touch and the inner body.
A prototype. Try it and the API answer with the RoBERTa model, but its readings are weak: the scores barely move from one sentence to the next.
OpenMorals™
LiveOpen models for moral framing in text, following Moral Foundations Theory.
Live. Try it and the API answer with the RoBERTa model; the Gemma model isn't served yet.
Environmentslet a model act
OpenSimulations™
LiveSimulated situations where a model acts: tools, a deadline, and every decision executed and logged.
Live. The site, Try it and the API, with three example scenarios. Keys are issued by the project.
Clientsbring the models and the people
AI Observability Studio
LiveRun one prompt through many models and watch them decide, side by side.
Live, in early access. Free to join.
Am I Conscious?
PreviewAn open experiment observing one persistent AI agent over time.
A demonstration site is live. The persistent agent hasn't started.
Scores are a classifier's reading of text. Simulated runs are simulated. No claim is made that any system is conscious.
6Open models
6Products
3Observers
1Environment
2Clients
How results are labelled ↗The models. On Hugging Face.
For each attribute, a small RoBERTa model and a larger Gemma model, fine-tuned for the same task. Download the weights, or call them through the API. Others can contribute a model.
Emotions · RoBERTaopen-emotions-roberta-125m-fp32Emotions · Gemmaopen-emotions-gemma4-e2b-bf16-loraMoral framing · RoBERTaopen-morals-roberta-125m-fp32Moral framing · Gemmaopen-morals-gemma4-e2b-bf16-loraSensations · RoBERTaopen-sensations-roberta-125m-fp32Sensations · Gemmaopen-sensations-gemma4-e2b-bf16-loraSmall products. Written contracts.
Observers
An observer is one attribute of text, the open models that read it, and an API. It takes a piece of text and returns a score for each label, with the model and version that produced it. It never takes part in the conversation.
Environments
An environment gives a model a situation, tools and a deadline. What the model calls is executed and logged, so its decision is something it did, not something it said.
Clients
A client runs the models and shows people the results. It attaches observers and environments with a URL and a key.
Build with it
A URL and a key.
Each product has its own API. An observer takes blocks of text and returns a score for every label, with the model and version that produced them. AI Observability Studio and Am I Conscious? connect this way, and so can any other platform.
Read an API guide ↗POST /v1/classify
curl https://www.open-emotions.com/v1/classify \
-H "Authorization: Bearer oe_live_…" \
-H "Content-Type: application/json" \
-d '{"blocks":[{"text":"Thank you so much!"}]}'