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
-
arcana
AI repositoriesEmbeddable RAG library for Elixir/Phoenix with agentic pipelines and dashboard
git clone https://github.com/georgeguimaraes/arcana.git -
awesome-ai-gateways
MCP serversAwesome AI gateways: open source and commercial LLM gateways, MCP gateways, agent (A2A) gateways, model routers, specs, and guides.
git clone https://github.com/ai-gateways/awesome-ai-gateways.git -
awesome-quant-ai
Docs & tutorialsA curated list of awesome resources for quantitative investment and trading strategies focusing on artificial intelligence and machine learning applications in finance.
git clone https://github.com/leoncuhk/awesome-quant-ai.git -
rightStage
Tools & appsSync AI context across every terminal window. 3 seconds to know what to work on next.
git clone https://github.com/warp-context/rightStage.git -
DeepPlanning
Datasets & benchmarksHugging Face dataset by Qwen
Qwen/DeepPlanning -
WindsurfAPI
AI repositoriesTurn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor. 把 Windsurf/Devin 云端 100+ 模型变成三套兼容 API。
git clone https://github.com/dwgx/WindsurfAPI.git -
oto-dock
Agents & frameworksThe self-hosted platform for your company's AI agents. Your team builds them on Claude Code, Codex or local models, and they work in chats, on schedules, on the phone and on your own machines.
git clone https://github.com/OtoDock/oto-dock.git -
AIPass
Agents & frameworksPersistent Agent Workspace — AI agents that remember, collaborate, and never start from zero.
git clone https://github.com/AIOSAI/AIPass.git -
Unity-MCP
MCP serversAI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.
git clone https://github.com/IvanMurzak/Unity-MCP.git -
Aegis
Agents & frameworksRuntime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.
git clone https://github.com/Justin0504/Aegis.git -
coding.sh
MCP serversOpen-source, local-first observability and evals for AI agents: see what Claude Code, Codex, Cursor and others did and what it cost.
git clone https://github.com/jackulau/coding.sh.git -
Everywhere
Agents & frameworksOn-screen aware AI assistant for your desktop. Uses current app context, multiple LLMs, and MCP tools to help you act across apps.
git clone https://github.com/Sylinko/Everywhere.git -
AuthorizationManagementClient
Public APIsRole based access control provides you a way to apply granular level policy administration down to individual resources or resource groups. These operations allow you to manage role definitions. A role definition describes the set of actions that can be performed on resources.
-
PageSpeed Insights API
Public APIsThe PageSpeed Insights API lets you analyze the performance of your website with a simple API. It offers tailored suggestions for how you can optimize your site, and lets you easily integrate PageSpeed Insights analysis into your development tools and workflow.
-
Z.ai: GLM 5
ModelsGLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...
z-ai/glm-5 -
Z.ai: GLM 4.7 Flash
ModelsAs a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...
z-ai/glm-4.7-flash -
Mistral: Mistral Medium 3.1
ModelsMistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...
mistralai/mistral-medium-3.1 -
OpenAI: GPT-4.1 Nano
ModelsFor tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
openai/gpt-4.1-nano -
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...
mistralai/mistral-small-3.1-24b-instruct -
{ "prompt": "You will perform an image edit using the person from the provided photo as the main subject. The face must remain clear and unaltered. Transform the subject into a solitary figure on a mist-shrouded wooden…
-
{ "prompt": "You will perform an image edit using the person from the provided photo as the main subject. Preserve his core likeness. The scene depicts Subject 1 as a beleaguered Victorian time traveler checking a…
-
{ "prompt": "You will perform an image edit using the people from the provided photo as the main subjects. The faces must remain clear and unaltered. Create a cute, humorous cartoon sticker design depicting the dad as…
-
WEIPING_COUNCIL
Agents & frameworksA local web app and CLI for anyone who wants to see where several LLMs disagree before trusting an answer: it sends one question to each model, has them review each other's answers anonymously, and returns a chairman's synthesis with the dissent and a trace of every model call.
git clone https://github.com/appleweiping/WEIPING_COUNCIL.git -
guardana
MCP serversOpen-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
git clone https://github.com/guardana/guardana.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.