Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
awesome-copilot-for-testers
Prompts👨💻 Instructions, prompts, and chat modes to help You with test automation for GitHub Copilot 🤖
git clone https://github.com/jaktestowac/awesome-copilot-for-testers.git -
One key, 100+ models: chat with any LLM, generate images and speech. Live model list. Free trial.
-
awesome-ai
PromptsMy ongoing WIP 🏗️ AI prompts, custom agents, skills & instructions - curated by me (and Copilot, ChatGPT, and Claude).
git clone https://github.com/anchildress1/awesome-ai.git -
omnicord
MCP serversDiscord server management MCP for AI agents: chat, moderation, admin, and full server building.
@orygn/omnicord@1.4.1 -
groq-mcp
MCP serversMCP server for Groq: fast LLM chat, model list. Needs a free API key.
@mrfentmen/groq-mcp@1.0.1 -
Discord MCP
MCP serversDiscord server management MCP for AI agents: chat, moderation, admin, and full server building.
@orygn/discord-mcp@2.0.0 -
trustai.center pay
MCP serversPay-per-use LLM inference for agents: pay in USDC/USDT or per call via x402. 247 chat models.
-
OpenAI: GPT Chat Latest
ModelsGPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...
openai/gpt-chat-latest -
DeepSeek: DeepSeek V3 0324
ModelsDeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
deepseek/deepseek-chat-v3-0324 -
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
qwen/qwen3-next-80b-a3b-instruct -
imp
Agents & frameworksRun large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.
git clone https://github.com/kekzl/imp.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.