Skip to content
SulluxPublic

About

The Channel Inference Engine is a high-performance continuous streaming inference engine with autonomic reflexes and full-fidelity long-term memory with near-instant recall.

Resources

Stars

6 stars

Watchers

0 watching

Forks

Latest commit

 

History

6 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Channel Logo

Channel Inference Engine

A high-performance continuous streaming inference engine with autonomic reflexes, written in pure Zig for Google's Gemma 4 models (gemma-4-E2B and gemma-4-12B-it).

Feel free to jump to our quick start guide to start chatting with your local streaming agent as soon as possible!


Documentation

Full architectural specifications, foundations, and API references are available on the official documentation website and in the docs/ directory:


License

Copyright © 2026 Sullux LLC. All rights reserved.

Channel is released under a dual-licensing model:

  • Personal & Non-Commercial Use: Free for personal, non-commercial, evaluation, and educational use. You may inspect, build, run, and modify Channel on your own hardware for personal experimentation.
  • Commercial Use: A commercial license is required for any commercial deployment, commercial product integration, SaaS hosting, or revenue-generating use. For commercial licensing inquiries and enterprise support, please contact Sullux LLC at licensing@sullux.com or visit sullux.com.

Warranty & Disclaimer

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL SULLUX LLC, THE AUTHORS, OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

About

The Channel Inference Engine is a high-performance continuous streaming inference engine with autonomic reflexes and full-fidelity long-term memory with near-instant recall.

Resources

Stars

6 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages