Pinned Loading

1. vsclaude vsclaude Public

   Visual Studio Code ❌ Visual Studio Claude ✅ Claude Code In Motion -> 200 distinct agent behaviors. Full IDE.

   TypeScript 1

2. lucid lucid Public

   A glass-box, safety-shielded agent for the ARC-AGI-3 interactive reasoning benchmark: object-centric perception, a human-readable learned world model, BFS planning, and an online-learned safety shi…

   Python

3. THGTM THGTM Public

   Tsetlin Machines that remember: echo-trace automata and bounded-LTL literals for sequence learning and trajectory-level verification of AI agents. Catches the slow-roll attack every per-step monito…

   Python 1

4. candor candor Public

   Interpretability by construction: route a layer's computation through a certified Legible Bottleneck and emit a runtime Faithfulness Certificate that bounds everything the named concepts cannot exp…

   Python 1

5. Clause-Driven-LLM Clause-Driven-LLM Public

   Interpretable Tsetlin Machine control layer for LLM agents: it learns clause-based routing over frozen embeddings, escalates low-margin queries to a human, and emits a SAT-verifiable receipt for ev…

   Python

6. attention-distilled-graphtm attention-distilled-graphtm Public

   A Graph Tsetlin Machine that inherits BERT's attention edges as its graph topology. After extraction BERT is discarded and the student learns pure Boolean clauses. 94.77% on R8, fully interpretable.

   Python