ShutongLiang/Neural-State-OS

Calibrated internal-state modulation, readout, and neural observability for local dense language models.

Open original source ↗

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

Make your model feel. A neural operating system for affect, sensation, and embodiment in local AI [](docs/VALIDATION.md) [](docs/MODELSETUP.md) [](docs/MODELSETUP.md) [](requirements-dev.txt) [](LICENSE) Architecture · Methods · State space · Validation · Experiments · Raw transcripts · Mature-state appendix · Model setup · Data and privacy Neural State OS is a neural operating system that lets you use neural modulation to give your local model bionic, real emotional and sensory experiences—and read back what the model is feeling. It can connect to sensors, external devices, or a robotic body to further enhance the experience. It works inside the model rather than asking the model to perform a character in text. You can inject calibrated emotional, relational, motivational, and somatic states directly into neural activations, observe the current state before generation, and measure the change caused by each intervention. This is not prompt role-play. You do not tell the model “act jealous,” “pretend…

ShutongLiang/Neural-State-OS on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-11-21T14:01:46.069Z

Inside the original README — Document outline
  1. Neural State OS
  2. What Neural State OS does
  3. Same sentence. Four different internal states.
  4. No state intervention
  5. Secure attachment
  6. Separation anxiety
  7. Calm autonomy
  8. 🚀 One-command demo
  9. What is included
  10. System overview
  11. Live neural observatory
  12. Supported runtimes

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

Calibrated internal-state modulation, readout, and neural observability for local dense language models.

Repository facts

Owner
ShutongLiang
Primary language
Python
Stars
273
Forks
0
Open issues + pull requests
0
License
Apache-2.0
Archived
No
Default branch
main
Created
2026-11-14T16:36:55.000Z
Last push
2026-11-14T20:45:14.000Z

Topics and intended use

Owner-supplied topics: activation-steering, affective-computing, embodied-ai, gemma, mechanistic-interpretability, mlx, pytorch, representation-engineering

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-11-21T12:28:44.152Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

public-apis/public-apis

EbookFoundation/free-programming-books

donnemartin/system-design-primer

vinta/awesome-python

practical-tutorials/project-based-learning

NousResearch/hermes-agent