- Boston, MA
- @sabinmthomas
- in/sabinthomas
Starred repositories
An open-source AI agent that brings the power of Gemini directly into your terminal.
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
Open Source AI Platform - AI Chat with advanced features that works with every LLM
🚀 The fast, Pythonic way to build MCP servers and clients
Droplet Agent is the daemon that runs on customer droplets to enable some features such as web console access.
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
Portable file server with accelerated resumable uploads, dedup, WebDAV, SFTP, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file
Using network observability to operate and design healthier networks
a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP
Infisical is the open-source platform for secrets, certificates, and privileged access management.
A high-throughput and memory-efficient inference and serving engine for LLMs
Explore java through small experimental programs.
List of ngrok/Cloudflare Tunnel alternatives and other tunneling software and services. Focus on self-hosting.
SafeLine is a self-hosted WAF(Web Application Firewall) / reverse proxy to protect your web apps from attacks and exploits.
The first open-source DDoS protection system
Connect your devices into a secure WireGuard®-based overlay network with SSO, MFA and granular access controls.
A Python notebook showcasing the use of Machine Learning for the task of bot detection, with an emphasis on e-commerce sites.
An open-source, self-hostable PaaS alternative to Vercel, Heroku & Netlify that lets you easily deploy static sites, databases, full-stack applications and 280+ one-click services on your own servers.
ODBC driver for MongoDB Connector for Business Intelligence
Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"
An extremely fast Python package and project manager, written in Rust.
Zenith - sort of like top or htop but with zoom-able charts, CPU, GPU, network, and disk usage
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
Awesome-LLM: a curated list of Large Language Model
MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

