模型与 AI 能力

Chat2API enables zero-cost access to leading AI models by leveraging official web UIs. It

GLM 5.3 Abliterated or Uncensored AI model — 35 jailbreak prompts, model guide and API. On

Uncensored AI models from RouterHub — the website for one-key API access to Claude, GPT, G

GLM 5.3 Uncensored — 35 jailbreak prompt files, model guide and API access. One RouterHub

Open-source local AI client and coding agent for DeepSeek, Qwen, ChatGPT and EconomyOS wit

八卦推演系统是一套将传统东方命理学与现代软件工程深度融合的开源全栈应用。项目以纯 Python 计算引擎为核心，严格依照古籍推算逻辑实现八字四柱、六爻占卜、紫微斗数、奇门遁甲、玄空

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/imag

DeepSeek reverse proxy, supports 896K context deepseek-flash (v4.1)

让 DeepSeek Harness(dsh) 在 HarmonyOS 完整跑起来：缓存优化对话预设 + 启动补丁 + 工具链 + 鸿蒙桌面/平板端客户端，node 不锁版本（最新

Local DeepSeek V4 proxy: reduces hallucinations strengthens system prompt following stop

Codex 接入 DeepSeek 的本地代理工具，支持双平台。A local proxy tool bridging Codex and DeepSeek, with dual-

Select inference providers for Cline API models, including DeepSeek and Z.AI. A Go proxy w

ClipAI — 跨平台智能 AI 剪贴板助手：支持全格式历史追溯与配额管理、全屏交互截图与独立高清查看器、多主流大模型图文对话（Gemini/OpenAI/DeepSeek/Cl

A simple AI app for Android 1.0+ with support for deep thinking, image perception, and web

让非多模态模型（DeepSeek 等）把图片识别委托给任意 OpenAI 兼容的多模态模型。零厂商硬编码，主模型支持视觉时自动隐藏自己。

This project is a web-based PDF question-answering chatbot powered by Deepseek v3 and R1's

OpenAI-compatible local proxy for Kiro CLI (Amazon CodeWhisperer) — Claude Opus 4.7, Sonne

API Scraper — Hunt down leaked API keys in GitHub commits, validate them against live endp

Contexts Optical Compression

Janus-Series: Unified Multimodal Understanding and Generation Models

A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoni

Visual Causal Flow

Daily AI by Dev: a public archive of short 60 to 90 second videos on AI tools, LLMs, codin

MCP vision proxy for DeepSeek text / Claude Code — multi-model fallback, compare_images, c

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xver

ParallelChat 是一款开源的多 AI 并行对话桌面应用，让你在一个界面中同时使用 ChatGPT、Kimi、Qwen、DeepSeek、GLM、Doubao、Yuanba

🌌 NexusVoice-2.5: The next-generation hands-free AI voice assistant. Features multi-model

将 OpenAI Responses API 请求翻译为 DeepSeek Chat Completions API 的流式代理，让 Codex 接入 DeepSeek 模型。St

FastTrack4LLM 是一个为大模型学习者准备的大模型学习与实践框架，帮助他们轻松掌握大模型的核心原理与训练流程，让每个人都能真正理解大模型的内部机制。本项目不仅完整复现了

MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's adva

🤖多模态 AI 聊天机器人 | 🚀 快速接入 微信、 QQ、Telegram、等聊天平台 | 🦈支持DeepSeek、Grok、Claude、Ollama、Gemini、OpenA

MCP 服务管理：增删改查与启停、连接测试、工具按需检索与全量注入、进程级与服务级环境变量（含密钥）；MCP service management: CRUD, connectio

DSH Ark Toolkit：为 DeepSeek Harness 接入字节火山方舟的文生图与语音合成能力。内置豆包 Seedream 文生图（ark_generate_imag

DSH native-mode MCP proxy: hide mcp__ tools from the model tool list, expose server-list/s

Route-compatible tool-result image hoisting: move images returned by tools onto the preced

DSH 插件：刷抖音 + 音频转写 —— 打开抖音网页版下滑浏览推荐视频，把看过的视频下载下来转成文字稿

DSH-for-AGI 开屏动画：9.9 秒精简版 + 30 秒剧场版。剧场版走完冷启动 → 自检 → 认知网络 → 工具桥接 → 上下文装配 → AGI 就位 → 交棒，装完或升

DSH Bundle：工作区级 MCP 配置。每个会话启动时读取该会话工作区根下的 .dsh/mcp.json，把声明的每个 MCP 服务器挂成 agent 作用域的 MCP cl

The official gpt4free repository | various collection of powerful language models | opus 4

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Att

A curated list of the best awesome AI plugins for AI assistants including Claude Code, Ope

免费大模型 API 导航 · 只收录能通过 API Key 和 endpoint 调用的永久免费 / 限时免费接口｜A curated list of free LLM APIs

AI API 公益站与 Token 中转站导航：GPT Claude Codex Grok Gemini DeepSeek 免费/低价 API

🍺 DeepSeek Harness (dsh) 酒馆与角色扮演插件精选 — 把酒馆搬进 agent | Curated tavern & roleplay plugins for

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

Independent DSH plugin inventory and transactional Profile manager.

A collection of recipes/notebooks showcasing use-cases of open-source models with Qubrid A

Windows Computer Use for AI Agents. Both a tool (22 MCP tools for click, type, screenshot,

Local-first beat library built for producers — catalog, BPM/key analysis, license tiers &

Windows desktop client for DeepSeek Harness — one-click launch, WebView2, tray mode, clean

Prompt Booster: A comprehensive tool for optimizing LLM prompts with version control, A/B

Hermes — a safety-first, voice-first Windows assistant: local STT -> DeepSeek reasoning ->

一款集合多家大模型能力的客户端。拥有丰富的个性化功能。现已支持：OpenAI，Ollama，谷歌 Gemini，讯飞星火，百度文心，阿里通义，天工，月之暗面，智谱，阶跃星辰，Dee

🌊 珊瑚口袋 AI (Coral Pocket) - 极致轻量的单文件 (Single-File) 跨平台 AI 聚合客户端。原生移动端体验 (Mobile-First PWA)，

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Gro

cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，mlops算法链路全流程，算力租赁平台，notebook在线开发，拖拉拽任务流pipeline编排，多机多

Personal AI Notebooks. Organize files & webpages and generate notes from them. Open source

Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysi

Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM,

LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, a

Cloud native, ultra-high performance AI&API gateway, LLM API management, distribution syst

A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, d

This is a WhatsApp AI bot that uses various AI models, including Deepseek, GPT, DALL-E, Ge

🐋 Полный гайд на русском: как установить и запустить DeepSeek локально (V4, R1) на ПК, Mac

MoE expert offload for low-VRAM GPUs — run 100B+ MoE models (DeepSeek, Qwen, Mixtral) on 8

让最新版 OpenAI Codex CLI / Codex 桌面端接入主流大模型的本地代理(新增mac/win包支持，后台运行，开机自动重启)。内置 小米 MiMo V2.5/De

💭 一个可二次开发 Chat Bot 单轮对话 Web 端 MVP 原型模板, 基于 Vue 3, Vite8, TypeScript, Naive UI, Pinia(v3),

Give Claude Code a cheap coworker. CLI tools that delegate bulk I/O to cheap LLMs (Kimi, D

Reproducible Docker/vLLM deployment, tuning, and benchmarks for DeepSeek V4.1 Flash on a s

🐍 Personal AI agent in pure Python — OpenClaw reimagined. Memory, RAG, skills marketplace,

Antigravity 跨平台桌面客户端：多账号管理与一键切号，让 IDE/App/CLI 接入 Claude、DeepSeek、GPT、Ollama 等模型 (BYOK) 并优化

Run the native 284B-A13B DeepSeek-V4-Flash-0731 LLM locally on one laptop CPU: pure C, 8 G

zen-proxy is a local translation proxy that bridges Claude Code's Anthropic Messages API w

DeepSeek-V4.1-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 297 tok/s for one user, up to

MCP server that delegates Claude Code subagents to local models (LiteLLM/llama.cpp/Ollama)

🎯 Free & open-source AI interview copilot. Real-time answers from voice + screenshots for

A lightweight, portable executable for invoking LLM with multi-API support - eliminating i

Translate anything on the web — with local LLMs (Ollama, LM Studio), cloud APIs (OpenAI, D

Open-source browser extension for bilingual web translation and YouTube subtitles in Chrom

Measured serving recipes for DeepSeek-V4.1-Flash on 4x NVIDIA DGX Spark (GB10): 1M context

Zero-dependency Universal AI Gateway & Smart Router for Node.js/Edge - Circuit Breakers, S

DeepSeek Harness plugin: local llama.cpp (llama-server) as a first-class model provider —

Self-hosted multi-modal AI server: chat/vision LLMs (Qwen, Llama, Gemma, DeepSeek), text-t

GemRouter is an OpenAI-compatible backend router for Gemini API, designed to maximize free

Windows turnkey installer that attaches a local Qwen3-VL vision model (llama.cpp) to DeepS

Pure-PyTorch DeepSeek-V3/K3-style LLM stack where every serving optimization ships with a

Run DeepSeek-V4.1-Flash (551B MoE, IQ2_XXS) locally on Apple Silicon with 128K context, ev

Run DeepSeek-V4-Flash-0731 on 4× RTX PRO 6000 with patched SGLang, fixing DSPARK crashes a

From-scratch Metal inference engine that runs DeepSeek-V4.1-Flash (233 GB GGUF) with 200K

Reproducible refusal-subspace editing and TP=2 deployment of DeepSeek V4 Flash 0731 on two

A powerful local proxy for Claude Code CLI and Codex CLI supporting NVIDIA NIM, Google,Gem

A Windows 11 voice assistant, rebuilt with DeepSeek-Pro-4. It listens for weak words, resp

8B reasoning LLM fine-tuned with DeepSeek-R1 + MLX LoRA on Apple Silicon. GGUF quantizatio

Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Cod

Optimized DeepSeek V4 Flash inference and serving on NVIDIA Ampere GPUs (SM80), based on M

Lightweight OpenAI-compatible proxy that lets Codex route Responses API traffic to NVIDIA

MCP server that lets Claude Code & Codex delegate bounded, token-heavy generation to local

Open-source LLM inference benchmarks — TTFT, TPOT, Throughput, Latency & Cost-per-token fo

LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, a

Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Cla