A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

Convert OpenAPI specifications to OpenAI function calling schemas and execute them with the official OpenAI Go SDK

Convert and invoke OpenAPI specifications as LLM tool/function definitions

A simple, secure MCP-to-OpenAPI proxy server

Focus on prompting and generating

Kandinsky 5.0: A family of diffusion models for Video & Image generation

Fully automatic censorship removal for language models

Smart-Control is a comprehensive solution for monitoring the status of disk devices and sending reports via a Telegram bot.

Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent. #1 on OpenRouter. 750k+ Kilo Coders. 6.1 trillion tokens/month.

Realtek RTL88x2BU WiFi USB Driver for Linux

Firmware to solve the USB 3.0/1 issues this USB3<->SATA has. (Disconnects, read/write issues etc)

🌅 a configurable motd generator

A cross-platform command-line utility that creates projects from cookiecutters (project templates), e.g. Python package projects, C projects.

Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and yo…

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Build reliable Gen AI solutions without overhead 🍕

Go library for embedded vector search and semantic embeddings using llama.cpp

Tools or function calling with gemma3

Набор инструментов интеграции с популярными сервисами и технологиями для 1С:Предприятие, OneScript и CLI (Telegram, VK, Bitrix24, Google, Яндекс, S3, PostgreSQL, SQLite, MySQL и др.)

implement GPT-OSS 20B & 120B C++ inference from scratch on AMD GPUs

Docker image unsloth with llama.cpp installed to export gguf after model training

A Go library for semantic caching with LRU eviction, supporting vector-based similarity search with pluggable embedding backends (local or cloud).

A serverless RSS feed for HuggingFace's Daily Papers

Go library for building LLM-based applications

Effective LLM Alignment Toolkit

Improved file parsing for LLM’s

🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

Unified management and routing for llama.cpp, MLX and vLLM models with web dashboard.