ai

Transformers PHP is a toolkit for PHP developers to add machine learning magic to their projects easily.

KV cache middleware for 1M context on 12GB VRAM. Uses K vectors as a retrieval index to fetch V on-demand from system RAM. No model modification, no retraining. Drop-in HuggingFace cache replacement.

Self-hostable content-addressed storage for AI models, datasets, containers, and build artifacts with Git LFS, OCI, Bazel HTTP, Huggingface, and Xet frontends

ArcMind Vector DB

Production-ready memory framework for AI agents. Dual-agent synthesis, self-evolution, composite scoring, multi-tenant isolation. REST API, Python SDK, CLI.

The holographic core for leOS

The blazingly fast in-memory vector database 🚀

GalaxDB is designed for AI and ML workloads that need more than a traditional database. Instead of stitching together a relational database, a vector store, an embedding API, and a training pipeline, GalaxDB provides all of these capabilities in one binary with a single SQL interface.

This project is a multi-modal AI voice assistant that uses LM Studio, OpenAI API or Claude Code, audio processing with WhisperModel, speech recognition, clipboard extraction, and image processing to respond to user prompts.

An invisible AI desktop assistant that evades screen capture and taskbar detection. Features instant visual analysis, live Whisper voice transcription, and robust support for premium LLMs (Anthropic, OpenAI, OpenRouter, Gemini, and local Ollama).

Multi-Agent Comic Generator powered by the @google-gemini API. Turn simple prompts into comics with AI-generated stories, consistent characters, auto speech bubbles, and 7 language support. Built with FastAPI and deployed on Google Cloud Run.

A slim, local-LLM-first AI coding assistant. TUI, Web UI, and desktop app. Runs air-gapped with Ollama, vLLM, or any OpenAI-compatible endpoint.

GLM-5.2 QuantTrio (Unpruned ) on 4xDGX Spark (GB10): 327K-655K context or up to 5 concurrent agents, one receipe. TP4 + DCP + MTP

Extend LLM context windows beyond GPU memory limits with disk-backed KV cache.

📑 npm pacakge to Craft files into Markdown with ease

Finetuning of Gemma-2 2B for structured output

Experimental tl;dr summaries for datasets on the Hugging Face Hub!

AI-native NoSQL + vector database with built-in semantic search for RAG, AI agents & LLM memory — the async Python client. Self-hosted Pinecone alternative.

An AI powered Video Serach Engine with google's SigLIP and Qdrant. It allows to search objects or key moments in videos just using natural language.

Exploring what HN is really thinking