Tirth Kanani
I build tools that help AI systems find the right context: less of it, better chosen.
I created code-review-graph and I am building CrumbleUX. Both turn messy signals into useful decisions.
Based in London. My MSc research at Birmingham explored traceable local language models; now I am testing auditable agents against ARC-AGI-3.
Selected work
code-review-graph
2026Local codebase context for coding agents
31,158 GitHub stars · up to 49× fewer tokens
CrumbleUX
2026An AI UX team that watches products being used
Founder · product, inference and infrastructure
Harmonic Flow Models for ARC-AGI-3
2026Auditable exploration for interactive abstract reasoning
Presented at Pre-ICML @ London 2026
Jailbreak-Eval
2025Adversarial testing for language models
Five attack generators · reproducible pilot baselines