Skip to content
View Bosc01's full-sized avatar

Block or report Bosc01

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.

Content in all repositories owned by your account will be closed.
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

Popular repositories Loading

  1. limit-order-book limit-order-book Public

    C++20 limit order book matching engine: 68.9M ops/s single thread on an Apple M5 (median of 5; mix of limit, market, cancel, modify), zero heap allocations, differential- and mutation-tested

    C++ 2

  2. stay stay Public

    AI dog-behavior triage that intercepts owners before shelter surrender: Claude-backed green/yellow/red severity engine, hard-coded bite and child escalation rules, 21 FastAPI endpoints over Supabas…

    Python 1

  3. nba-scout-agent nba-scout-agent Public

    Claude tool-use agent that writes basketball scouting reports: 7 tools across Basketball Reference, ESPN, EuroLeague and FIBA, 5-call budget per report, 24h Redis cache, wrong-player validation exp…

    Python 1

  4. teamos-prd-assistant teamos-prd-assistant Public

    PM workflow tooling built during a HashiCorp internship: GitHub issue signal pipeline with recency-weighted scoring and TF-IDF/KMeans topic clustering, plus a Slack approval tracker with a full aud…

    Python 1

  5. vecstore vecstore Public

    Brute-force and HNSW vector indexes written from scratch in NumPy, benchmarked against FAISS: p50/p95/p99 latency, Precision@K, Recall@K, MRR, and higher recall than FAISS HNSW at matched M, efCons…

    Python 1

  6. medical-case-retrieval-agent medical-case-retrieval-agent Public

    Cross-encoder reranking between FAISS retrieval and generation over 764 PubMed case reports. P@5 +9.2% surviving Benjamini-Hochberg, with the negative results kept: the gain vanishes under strict r…

    Python