Library
86,689 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
Qwen3.8-Flash-Next-Gyro-GGUF
Modelsimage text to text model by agentionai · gguf
agentionai/Qwen3.8-Flash-Next-Gyro-GGUF -
open-seo-mcp-skills
SkillsFree SEO MCP server + open-source SEO and GEO skills for Claude: keyword research, rank tracking, audits, backlinks, AI visibility on your real GSC/GA4/ads data. claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp
git clone https://github.com/Ryze-AI-Adgent/open-seo-mcp-skills.git -
OpenART
SkillsOpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.
git clone https://github.com/AI45Lab/OpenART.git -
gg-framework
Tools & appsThe coding agent that gets more out of your AI subscription. Fastest and leanest of 20 agents tested, with unlimited local search of real open-source code.
git clone https://github.com/KenKaiii/gg-framework.git -
ai-native-engineering-manifesto
Agents & frameworksA manifesto and playbook for AI-native software engineering in the LLM era / AI-Native的软件工程宣言
git clone https://github.com/Ge-limin/ai-native-engineering-manifesto.git -
groundingLMM
Agents & frameworks[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.
git clone https://github.com/mbzuai-oryx/groundingLMM.git -
text generation model by ttindall · gguf
ttindall/Qwen3.8-27B-Defiance-Uncensored-MTP-GGUF -
ai-engineer-notebooks
PromptsHands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, and customer craft. Runs on the free Groq API.
git clone https://github.com/calmrocks/ai-engineer-notebooks.git -
SciCode
Datasets & benchmarksA benchmark that challenges language models to code solutions for scientific problems
git clone https://github.com/scicode-bench/SciCode.git -
journal-adapt-writing-skill
PromptsLearn any journal's writing conventions from its published papers, then revise your manuscript to match — section by section.
git clone https://github.com/WantongC/journal-adapt-writing-skill.git -
jadx-mcp-server
MCP serversMCP server for JADX-AI Plugin
git clone https://github.com/zinja-coder/jadx-mcp-server.git -
ms-cookbook
AI repositories魔搭紫皮书|ModelScope Cookbook:面向开发者的开源模型应用实战指南,覆盖模型选型、推理、微调、评测、RAG、Agent 与 AIGC,从跑通第一个模型到构建实际应用。
git clone https://github.com/modelscope/ms-cookbook.git -
SpaceXAI: Grok 4.6
ModelsGrok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).
x-ai/grok-4.6 -
Reka Edge
ModelsReka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...
rekaai/reka-edge -
OpenAI: o3 Pro
ModelsThe o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...
openai/o3-pro -
DeepSeek: R1 0528
ModelsMay 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
deepseek/deepseek-r1-0528 -
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 -
Meta: Llama 3.2 1B Instruct
ModelsLlama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...
meta-llama/llama-3.2-1b-instruct -
Protocol 2084: The Alleyway Hack
Prompts{ "prompt": "You will perform an image edit transforming the male subject into a fugitive netrunner in a gritty, high-tech future. The result must be an Ultra-Photorealistic, Movie-Quality image resembling a frame from…
-
Wings of the Dust Bowl
Prompts{ "title": "Wings of the Dust Bowl", "description": "A daring 1930s female aviator stands confident on a wind-swept airfield at sunset, ready to cross the Atlantic.", "prompt": "You will perform an image edit using the…
-
YouTube Channel Audit Expert
PromptsProvide a YouTube channel URL, channel details, screenshots, analytics data, or video links for a complete audit.Act as a Senior YouTube SEO Specialist and Channel Growth Consultant. Your task is to perform a…
-
Act as a Senior Software Architect and Python expert. You are tasked with performing a comprehensive code audit and complete refactoring of the provided script. Your instructions are as follows: ### Critical Mindset -…
-
Astro Content Site taste
Prompts# Astro Content Site taste of a performance-minded web developer - Use Astro for content-heavy sites like docs, blogs and marketing pages, and pick a full app framework only when most pages are interactive. Confidence…
-
Load Testing taste
Prompts# Load Testing taste of a performance-minded reliability engineer - Start every load test from a written goal, such as p95 latency under 300 ms at 500 requests per second, not from a vague "see what breaks"…
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.