A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

DoCoreAI is a next-gen open-source AI profiler that optimizes reasoning, creativity, precision and temperature in a single step—cutting token usage by 15-30% and lowering LLM API costs

Code respository for AutSPACEs: the Autistica/Turing citizen science platform

Collective Knowledge repository with actions to unify the access to different predictive analytics engines (scipy, R, DNN) from software, command line and web-services via CK JSON API:

Locally hosted AI Agent Python Tool To Generate Novel Research Hypothesis + Titles + Abstracts

A post-symbolic physics framework modeling intelligence, collapse, and emergence through entropy flow.

Modular framework for building self-modeling artificial agents with explicit internal state representation and meta-cognitive capabilities. Includes RL, hybrid, and dummy policies with integrated SelfModel monitoring and scientific metrics.

A basic Calkit project example.

Open research for sustainable compression intelligence — powered by the private SRC Engine core.

🌐 Explore SRC Research Lab, a secure platform for benchmarking and developing the Semantic Recursive Compression Engine with reproducible results and cost-aware metrics.

Hobby open research project which aims to demonstrate the capabilities of PT net (Petri net) based formal methods in improvement of producer/consumer pipelines