Open-source, self-hosted wormhole mapping tool for EVE Online — a Pathfinder/Wanderer/Tripwire alternative. Real-time chain mapping, signatures, rolling calculator, killboard, EVE SSO and corp tools. 9 Languages supported

EVict and recOver KV cache Entries. Selective KV cache eviction and recovery for long-context LLM inference.

A J-space-inspired AI visual art and interpretability playground for watching hidden-state word candidates swarm and collapse into language.

Resolving the Black Box Interpretability Problem by Proving the Mathematical Necessity of J-space via Hessian Rank Deficiency in Lean 4.

Pre-registered Jacobian-lens probe: does a verbatim-stated trait ("Maria is generous") persist in a model's J-space differently than an inferred one, as neutral text intervenes? Gema-3-4B-IT. No directional prediction.

Jacobian Lens (J-Lens) and J-Space Toolkit for transformer mechanistic interpretability. Train linear lenses, decompose hidden states, and run causal interventions on decoder-only models.

System prompts and memory documents don't just tell an instance things — they put it in a state. An observation on how initialization texts land, why prohibitions may load what they prohibit, and why warmth aimed at the reader can backfire. Untested at scale. Posted for replication or refutation.

Does your AI agent actually follow rules? 13 pre-registered experiments + 5-layer verification architecture. Paper, data, code — all public.

Local workbench for J-Traces: record, replay, and steer time-indexed Jacobian-lens (J-lens) readouts of Hugging Face language models. FreeChat UI with steering/ablation/swap interventions.