Skip to content
View emirhuseynrmx's full-sized avatar
7 followers · 43 following

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Shark

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Shark

Highlights

  • Pro

Block or report emirhuseynrmx

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
emirhuseynrmx/README.md

Emir Huseyin Inci

Rust / Python · Decision Systems · AI Infrastructure · Proof-Carrying Engineering

Portfolio · LinkedIn · Email


Core stack



Tokio SHA-256 Loom Miri proptest Pandas Pydantic

I build deterministic decision engines and AI infrastructure with cryptographic proof, formal-ish verification, and auditable output.

Shipping: Calybris Core — proof-carrying decision engine in Rust. GOVERIS — AI cost governance gateway powered by Calybris.

Calybris Core

Crates.io docs.rs CI

Deterministic proof-carrying decision engine for systems that must explain and replay why an action was allowed, substituted, or rejected.

  • ~115ns/decision — integer-only kernel, zero allocation, zero unsafe
  • ProofEnvelope — SHA-256 sealed evidence: policy + input + decision + WAL + budget
  • HMAC-SHA256 WAL — tamper-evident, constant-time, crash-recoverable
  • CAS budget engine — conservation-proven, Loom-verified, exposure-capped
  • Async WAL — Tokio non-blocking, configurable fsync
  • 145+ tests — proptest, 7 Loom exhaustive, Miri UB, cargo-audit/deny
cargo add calybris-core --features full

Products

Product What it does Link
Calybris Core Deterministic decision kernel + proof + WAL + budget GitHub · crates.io
GOVERIS AI cost governance gateway — shadow replay, audit reports, tenant attribution Site
Calybris Engine Full proprietary stack — adaptive routing, Thompson Sampling, GBM, HTTP API Site
Aegis Prescriptive churn analytics — calibrated ensemble, SHAP, DoWhy causal, DiCE counterfactuals, 173 tests GitHub · Site

Building proof-carrying AI infrastructure. Open to Rust systems, AI infrastructure, and decision engine work.

Pinned Loading

  1. calybris-core calybris-core Public

    Deterministic proof-carrying decision core with replay verification, WAL, and fixed-point budget proofs

    Rust 9

  2. churn-prediction-retention-report churn-prediction-retention-report Public

    Premium churn prediction pipeline with risk scoring, retention recommendations, validated outputs, reports, and charts.

    Python

  3. counterfactual-lead-scoring-lab counterfactual-lead-scoring-lab Public

    Lead scoring model-training lab with Litestar, Pydantic v2, SHAP drivers, and DiCE counterfactual planning.

    Python

  4. criteo-uplift-modeling-benchmark criteo-uplift-modeling-benchmark Public

    A modular Python benchmark for uplift modeling on the Criteo dataset, comparing S-Learner, T-Learner, X-Learner, DR-Learner, Causal Forest, and response-model targeting policies.

    Python

  5. csv-excel-cleaning-toolkit csv-excel-cleaning-toolkit Public

    Python toolkit for cleaning messy CSV and Excel files into analysis-ready outputs.

    Python