3 projects
hypermcts
Honest test-time compute (AE-MCTS) + projected KV-cache memory accounting for local/edge LLMs. Every metric is real or explicitly labeled simulated.
termmind
AI-powered terminal assistant — 9 LLM providers, security scanning, code generation, prompt library, 50+ commands
ai-trust-validator
Validate AI-generated code for security vulnerabilities, hallucinations, and logic errors