ShutongLiang/Neural-State-OS
Library
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 3 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 2 days ago.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
Provides tools to inject calibrated emotional, relational, motivational and somatic state vectors into the residual streams of local Gemma models, read the resulting internal state before generation, and compare outputs with modulation on and off. Includes a 31B CUDA runtime, a…
Who it's for
Researchers and developers studying activation steering and interpretability in local Gemma language models on CUDA or Apple silicon
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up ShutongLiang/Neural-State-OS in my project. Follow its README: https://github.com/ShutongLiang/Neural-State-OS. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/ShutongLiang/Neural-State-OS?ref=badge)Similar repos
- canivel/dynolab
A free, open-source Mac app for running AI models locally (MLX or GGUF) and investigating their behavior. It captures internal activations, runs probes and interventions, saves experiments in a local
- lyramakesmusic/neuron-explorer
A steering-first explorer for Qwen3.5-4B that pushes every MLP neuron in a layer up and down on a few prompts, keeps all rollouts, and lays the results out in a 3D view of the model. It also runs a li
- recursive-oss/rec
Local inference engine for running Recursive's Flint language models on Apple Silicon Macs. Provides an OpenAI-compatible chat-completions API on localhost and pre-configured launchers for the pi and
- eust-w/opengeniemaster
A zero-dependency Python framework that exposes embodied robot execution, multimodal guidance, physical feedback and task continuity as an MCP server, so coding agents can drive multi-robot work. It a
- Yuuyuko-uu/dsh-feiyu-mood
A DSH plugin that gives an AI companion a mood value. After each turn, the model judges whether the mood rises or falls, adjusts seven emotion values, and records a short reason. Mood decays back towa
- AmSach/maple
Research project that prunes low-activation experts from Mixture-of-Experts LLMs using routing statistics from a calibration corpus, with a reference Gemma 4 26B-A4B model reduced to about 4.75 GB for