this one needs a pointer and a wider screen
The explorer is a 3D graph you orbit and descend into. It doesn't survive translation to a small touchscreen, and a compromised version is worse than none — everything in it is on the main page, in text.
← read it flat insteadA navigable graph of my work, structured the way chrono-mind navigates vectors: sparse overview on top, full detail below.
A temporal vector store — time treated as a first-class axis of similarity, not an afterthought.
HNSW graphs with native temporal decay and importance weighting, over memory-mapped storage and lock-free concurrent operations.
A real query, running. It enters at the sparse top layer and descends greedily — touching a handful of nodes instead of all of them. Toggle decay to let recency compete with similarity.
Rust, HNSW, temporal decay, lock-free, memory-mapped
CodeA behavioral layer that turns human state into machine-consumable interaction constraints for LLMs.
23 interpretable axes; a pure behavioral layer that produces prompt context, not actions. Explicit non-goals: no action execution, no persuasion optimization, no hidden optimizers.
23 interpretable axes collapse into a state vector, which a rule-based translator turns into prompt constraints. It emits context, never actions.
Rust + Python, sub-500µs, 85% validation pass, model-agnostic
CodeBitcoin UTXO management and off-chain state for payment channels.
Merkle-based state proofs give O(log n) verification; deterministic signature ordering prevents replay. Built for provable, auditable state transitions.
Click any leaf to prove it. The 3 siblings you are handed light amber; the chain you recompute goes cool. Then tamper with it and watch the root stop matching.
Rust, Merkle proofs, sub-ms transitions, 60% faster, ~2MB / 1000 UTXOs
CodeMulti-agent graph intelligence — natural-language querying over agent-interaction graphs.
Schema-agnostic backend that evolves JSON schemas at runtime; NL translated into safety-constrained AQL (whitelisting, result caps). Refactored the LLM subsystem down ~84% while improving reliability.
Agent interactions land in a graph store under schemas registered at runtime. Natural language becomes AQL — but only through a safety gate.
Python, ArangoDB, FastAPI, 80+ tests
BackendFrontendA verification gate that commits only the claims a source actually supports.
Cross-family LLM cross-checking as a correctness layer: unsupported claims are dropped, not softened.
Run the gate with one verifier, then with two from different families, and watch which fabrications survive the first pass.
Python, grounded falsification, cross-model
CodeReverse-engineered a credential-theft NPM package disguised as a recruiter take-home.
Traced obfuscated payloads through fake passport middleware into a staged execution pipeline; reported the package to NPM for takedown.
The infection path, one step at a time — from the recruiter message to the takedown.
Node.js, deobfuscation, threat analysis
Watch