ai

A reasoning assistant for your STEM education

Official Core Services for MemFuse - the lightning-fast open-source memory layer that gives LLMs persistent, queryable memory across conversations and sessions.

Code for Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense? [COLM 2024]

Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.

VL-JEPA inspired pipeline — compress images/text locally via Ollama, send compact payloads to any LLM API. Cut token costs by ~80%.

Fast dataset format and loader

a rust crate for easily implementing faster-whisper stt into your rust programs.

A fluent State-of-the-art [Speech-To-Text] API to your PHP/Laravel applications

whisper.cpp Windows binary w/ Vulkan GPU support

MinimalGPT is a concise, adaptable, and streamlined code framework that encompasses the essential components necessary for the construction, training, inference, and fine-tuning of the GPT model. This framework is implemented exclusively using Keras and TensorFlow, ensuring compatibility and coherence within the broader deep learning ecosystem.

A curated list of the best AI resources, courses, tools, and repositories. Covering Generative AI (GenAI), LLMs, RAG, AI Agents, Prompt Engineering, and more. Your go-to cheat sheet for all things AI.

A translation app for Bahasa Melayu to English with support for Manglish and bahasa pasar.

🐬 Formation MariaDB 12.3 LTS : SQL, index, transactions, réplication, Galera, MaxScale, DevOps/Kubernetes et MariaDB Vector (IA/RAG). 20 modules.

An application that enable the users to upload PDF files and ask questions regarding their content using Retrieval Augmented Generation (RAG)

Model uses Whisper, CHATGPT, GTTS

Unofficial No Such Thing As A Fish episode transcripts.

CyberBrain_Model is an advanced AI project designed for fine-tuning the model `DeepSeek-R1-Distill-Qwen-14B` specifically for cyber security tasks.

Meshery Academy for TCS Labs

Download Huggingface repositories without the need to install dependencies

Minimal, async-first Python framework for production LLM apps- 2 hard deps, no magic, no SaaS.