What I'm building.
Each one is a working prototype, not yet a product or a company. The architecture, the numbers, the honest status — all on these pages.
Avarna Privacy Gateway
3-layer PII detection · 97% accuracy · sub-second round-trip on consumer GPUs. Encrypted entity graph. Model-agnostic.
Stock Predictor
Quantitative model exploration combining classical features and learned representations. Details & results to come as the POC matures.
Multi-Agent Platform
An orchestration substrate for agent collaboration — planning, tool-use, memory, evals. Architecture write-up when the v0 is stable.
Other explorations
Small, sharp experiments — released under permissive licenses. The full list will surface here once the GitHub feed is linked.
Privacy you can prove, not just promise.
A drop-in gateway between your apps and any LLM provider. Three detection layers in parallel, an encrypted entity graph, and a round-trip you can put on a chart. Status — working prototype; no company yet.
Avarna intercepts AI traffic before it leaves your perimeter — detecting PII with three layers in parallel, masking it, holding the cleartext-to-token map in an encrypted entity graph, and unmasking the model's response on the way back.
The prototype already supports full provider choice — Claude, GPT, open-weights — without the compliance headache. Self-hostable. Model-agnostic. With an auditable trail of every prompt and every byte that crossed the wire. It is a POC today, not a product yet.
Pipeline · Detect → Mask → Entity Graph → Unmask
A quantitative exploration.
Combining classical features with learned representations — a POC for testing whether modern ML pipelines can produce signal beyond the noise floor. Methodology and results land here as the experiment runs its course.
Status: in progress. Repo: [private until v0]. Watch this section for the writeup.
Substrate for agent collaboration.
A working prototype of how multiple agents can plan, share tools, and hand off context — with evals at every seam. Architecture diagram and first results will publish when v0 stabilizes.
Status: design + prototype. Repo: [private until v0]. Detailed writeup pending.
Small, sharp experiments.
Permissive-licensed tools, side experiments, and one-day hacks. Once the GitHub feed is wired up, the most recent will surface here automatically.
Status: placeholder. Drop GitHub username in memory/user_profile.md and the agent will pull repos in on the next weekly run.