-
CS PhD @ UofT
- Toronto, Canada
- https://www.cs.utoronto.ca/~smaghrebi/
- in/smaghrebi
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Starred repositories
Postgres extension for vector search (DiskANN), complements pgvector for performance and scale. Postgres OSS licensed.
Datasets for approximate nearest neighbor search
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
An open-source AI agent that brings the power of Gemini directly into your terminal.
Falconn++ is a locality-sensitive filtering (LSF) approach, built on top of cross-polytope LSH (FalconnLib) to answer approximate nearest neighbor search with inner product.
Open source clone of the Risk board game
MimiClaw: Harness on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS. Hardware agents OS.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A library for efficient similarity search and clustering of dense vectors.
A web app for tracking your movies, TV shows, anime, manga, books, games and music.
Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…
State-of-the-Art Source Code Plagiarism & Collusion Detection. Check for plagiarism in a set of programs.
🔎 Open source distributed and RESTful search engine.
Free and Open Source, Distributed, RESTful Search Engine
Render markdown on the CLI, with pizzazz! 💅🏻
Constant time rank & select queries on bit vectors, with especially low overhead.
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
The first range filter to simultaneously support dynamic operations, variable-length keys, range queries of any length, and high performance while providing a theoretical false positive rate guaran…
Keigo: a fast, persistent, and parallelism-aware hierarchical storage middleware for LSM-based KVS.