deepseek

Local AI Music Discovery for Lidarr - Brainarr is a privacy-focused AI-powered import list plugin for Lidarr that generates intelligent music recommendations using local AI models. It exclusively supports local providers (Ollama, LM Studio) to ensure your music preferences never leave your network.

🚀 Engram-PEFT: An unofficial implementation of DeepSeek Engram. Inject high-capacity conditional memory into LLMs via sparse retrieval PEFT without increasing inference FLOPs / DeepSeek Engram 架构的非官方实现。通过参数高效微调 (PEFT) 为大语言模型注入超大规模条件记忆，支持稀疏更新且不增加推理开销。

Persona Control Language (PCL)

ReAct AI Agent from Scratch using DeepSeek: Handling Memory & Tools without Frameworks

AMG-RAG (Agentic Medical Graph-RAG) is a comprehensive framework that automates the construction and continuous updating of Medical Knowledge Graphs (MKGs), integrates reasoning, and retrieves current external evidence for medical Question Answering (QA).

macOS voice productivity app — built-in dictation, AI rewrite, and translation. Powered by local Whisper + LLM.

🐍 Personal AI agent in pure Python — OpenClaw reimagined. Memory, RAG, skills marketplace, cron, voice. Telegram/Discord/WhatsApp/Web. Works with DeepSeek, Claude, Gemini, Kimi, GLM, Ollama.

NPX/Docker package that creates Ollama API server and forward requests to Gemni/OpenAI/Deepseek/Kimi K2. Mainly purpose to use Free tier APIs in Jetbrains AI Assistant

中文网文写作工具包 · Chinese web-novel writing toolkit (23 skills) — a Claude Code plugin, also works in ChatGPT / DeepSeek / Gemini

Ollama Zig library

An AI-powered solution designed to enhance mobility for visually impaired individuals by combining real-time video analysis with voice-guided navigation. Also features a built-in Multi-Agent AI Assistant — users can speak naturally to complete map navigation, adjust system settings, send messages to family.

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.

A Chat Client for LLMs, written in Compose Multiplatform.

Real-time bilingual subtitles for any browser video. Offline-first speech recognition (Whisper + SenseVoice, 100+ languages) with local Ollama AI translation — 100% private, ultra-low latency.

Prompt Library is an open-source, high-quality AI prompt repository that supports multiple languages and categorized search, helping you efficiently explore the unlimited potential of AI.

PsyChat 是一款基于范例引导与Agentic RAG的智能 AI 心理咨询助手。基于高度匹配的Few-shot与学习笔记，应用理性情绪行为疗法（REBT）帮助用户识别并调整非理性信念，缓解负面情绪。

ComfyUI custom nodes for DeepSeek, Qwen, GPT, and other OpenAI-compatible LLM APIs, with tools for chat, translation, vision, and JSON workflows.

A web-based memory usage and performance calculator for Huggingface GGUF models

Ultra-Intelligent AI-in-one Application Platform | 至数云-超轻量智能应用平台/智能平台

This project is the backend engine for a fully autonomous AI-powered call center. It integrates a large language model (LLM), speech recognition, and text-to-speech to manage real-time phone conversations via Asterisk.