Library
87,608 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
neuron-laravel
AI repositoriesOfficial Neuron AI Laravel SDK
Source for neuron-laravel (opens github.com) git clone https://github.com/neuron-core/neuron-laravel.git -
ShibaClaw
Agents & frameworksSelf-hosted personal AI agent with a WebUI, memory, tools, MCP, sub-agents and automations. Connect local or cloud LLMs.
Source for ShibaClaw (opens github.com) git clone https://github.com/RikyZ90/ShibaClaw.git -
ollama-benchmark
Datasets & benchmarksOllama based Benchmark with detail I/O token per second. Python with Deepseek R1 example.
Source for ollama-benchmark (opens github.com) git clone https://github.com/LarHope/ollama-benchmark.git -
agentos
Agents & frameworksThe agent OS that evolves itself.
Source for agentos (opens github.com) git clone https://github.com/iii-experimental/agentos.git -
cozempic
SkillsContext cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning
Source for cozempic (opens github.com) git clone https://github.com/Ruya-AI/cozempic.git -
ktx
Skillsktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company
Source for ktx (opens github.com) git clone https://github.com/Kaelio/ktx.git -
Swift-1.5-Qwen3.8-27b
Modelsimage text to text model by ukisai · transformers
Source for Swift-1.5-Qwen3.8-27b (opens huggingface.co) ukisai/Swift-1.5-Qwen3.8-27b -
claude-code-workflows
SkillsDevelopment workflows for Claude Code that keep broad exploration focused on the outcome you approved.
Source for claude-code-workflows (opens github.com) git clone https://github.com/shinpr/claude-code-workflows.git -
core
AI repositoriesAI-powered CMS core for personal blogs and creator websites, with AI summaries, translation, moderation, and writing workflows.
Source for core (opens github.com) git clone https://github.com/mx-space/core.git -
gemini-web-to-api
AI repositories✨Reverse-engineered API for Gemini web app. It can be used as a genuine API key from OpenAI, Gemini, and Claude.
Source for gemini-web-to-api (opens github.com) git clone https://github.com/ntthanh2603/gemini-web-to-api.git -
NeuroSploit
Agents & frameworksNeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various aspects of offensive security operations.
Source for NeuroSploit (opens github.com) git clone https://github.com/JoasASantos/NeuroSploit.git -
OSWorld-V2
Datasets & benchmarksOSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
Source for OSWorld-V2 (opens github.com) git clone https://github.com/xlang-ai/OSWorld-V2.git -
mnemosyne
MCP serversAuditable, local-first memory for AI agents in one SQLite file. MCP server for Claude Code, Cursor and Codex. npm: mnemosy-ai
Source for mnemosyne (opens github.com) git clone https://github.com/28naem-del/mnemosyne.git -
nagi-bench
Datasets & benchmarksOne-shot LLM eval cases by NAGI STUDIO - same prompt, different agents (model + harness), runnable artifacts side by side.
Source for nagi-bench (opens github.com) git clone https://github.com/nagi-studio/nagi-bench.git -
generalbots
Agents & frameworksMulti-agent AI platform for autonomous agents, agentic AI orchestration and LLM workflow automation. 80 self-hosted apps - Chat, CRM, Mail, Drive, Calendar, Advanced RAG. Open source, built in Rust.
Source for generalbots (opens github.com) git clone https://github.com/generalbots/generalbots.git -
awesome-ai-product-management
Docs & tutorials🤖 Resources for AI product managers.
Source for awesome-ai-product-management (opens github.com) git clone https://github.com/aza-ali/awesome-ai-product-management.git -
rust-docs-mcp-server
Tools & apps🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.
Source for rust-docs-mcp-server (opens github.com) git clone https://github.com/Govcraft/rust-docs-mcp-server.git -
amfs
Agents & frameworksRecursive Self-Improvement for AI agents and models, helping your agents self-improve with every run
Source for amfs (opens github.com) git clone https://github.com/raia-live/amfs.git -
genex-desktop
Agents & frameworksDesktop app for game dev with AI: make games in Unreal Engine, Unity, Godot or the browser. The agent sets up the engine, builds your game and play-tests it by itself.
Source for genex-desktop (opens github.com) git clone https://github.com/genex-games/genex-desktop.git -
sigmap
Tools & apps~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server
Source for sigmap (opens github.com) git clone https://github.com/manojmallick/sigmap.git -
llm-value-rankings
Datasets & benchmarksDaily LLM value rankings - compare 300+ models by intelligence, speed and price. OpenRouter + Artificial Analysis. 大模型性价比排行榜
Source for llm-value-rankings (opens github.com) git clone https://github.com/yyh-001/llm-value-rankings.git -
image text to text model by drowzeys · transformers
Source for DeepSeek-V4.1-Flash-Abliterated-Cybersecurity-Unleashed (opens huggingface.co) drowzeys/DeepSeek-V4.1-Flash-Abliterated-Cybersecurity-Unleashed -
hermes-official-plugins
AI repositories☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog.
Source for hermes-official-plugins (opens github.com) git clone https://github.com/NousResearch/hermes-official-plugins.git -
sandboxd
Tools & appsOpen-source, self-hosted AI app builder — an agent builds real apps in isolated sandboxes on your own server, each live at a preview URL. Self-host in one command. MIT.
Source for sandboxd (opens github.com) git clone https://github.com/tastyeffectco/sandboxd.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.