Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.
- anthropic-api
- cuda
- gemma
- gguf
Official CLI for the OpenAI API
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
A simple tool to select files from a repository to copy/paste into an LLM
A local-first AI knowledge base & NotebookLM alternative built with Electron.
Read it. See it. Get it. Built at GDG AI Hack Milan 2026 for "Learn Different" track.
Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.
Boot operating systems directly from ISO/WIM images
- grub2
- multiboot
- usb
- bootable-usb
Loki: Open-source solution designed to automate the process of verifying factuality
- ai
- factuality
- hallucination
Get answers for CLI commands from ChatGPT right from your terminal
Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.
LangChain powered shell command generator and runner CLI
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC
This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库,目标就是: 👉 把 Claude Code 从“对话式编码工具”,变成 可设计、可复用、可治理的工程系统。
A neural network trained to help writing neural network code using autocomplete
基于本地代理的方式,绕过 IDE 的固定模型服务商限制
The repository host gives no description.
EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluation code.
Xiaomi-OCR-0
基于官方OpenWebUI,汉化界面提高中文使用体验,增加了模型计费和用量统计
真实 API 定价:订阅月费 ÷ 实际可用 token,含额度、单价与分榜帕累托图。Real API pricing: subscription fee ÷ usable tokens, with allowance, unit-price, and leaderboard Pareto charts.
a self-hosted webui for 30+ generative ai
- bark
- controlnet
- gfpgan
- gradio
PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations.