Library
85,762 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 connect AI to my tools
-
llmtrim
PromptsLocal proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).
git clone https://github.com/fkiene/llmtrim.git -
skillcheck
PromptsBlind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.
git clone https://github.com/sx4im/skillcheck.git -
Moe-s-Tavern
MCP serversAI agent task board for Claude Code, Codex, Gemini CLI and Grok Build: plan, approve, build and review inside JetBrains or VS Code, with state in .moe/ in your repo
git clone https://github.com/yaront1111/Moe-s-Tavern.git -
curated-claude-code
SkillsA small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.
git clone https://github.com/Sanexxxx777/curated-claude-code.git -
repertoire-ai
SkillsThe lockfile for agent skills. A package manager with named catalogs, a digest per target, and a manifest you commit. 30+ agents, no telemetry.
git clone https://github.com/phillarmonic/repertoire-ai.git -
mavericks-os
SkillsOrchestrate Claude Code sub-agents across long-running, single- or multi-repo projects. Artifact-first state, task lifecycle, cross-repo dependencies and QA gates that survive every session - not buried in chat history.
git clone https://github.com/yahor-punko/mavericks-os.git -
Registry API
Public APIsThe Registry service allows teams to manage descriptions of APIs.
-
App Store Connect API
Public APIsOpenAPI description for apple.com:app-store-connect.
-
The Jira Cloud platform REST API
Public APIsJira Cloud platform REST API documentation
-
GameSparks Game Details API
Public APIsThe API to manage the GameSparks game details
-
Custom Vision Prediction Client
Public APIsOpenAPI description for microsoft.com:cognitiveservices-Prediction.
-
Custom Vision Training Client
Public APIsOpenAPI description for microsoft.com:cognitiveservices-Training.
-
ThumbGate
MCP serversThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
git clone https://github.com/IgorGanapolsky/ThumbGate.git -
openai-codex-agent-skills
SkillsCurrent Codex instructions, 39 engineering skills, and portable settings with Windows and Linux installers.
git clone https://github.com/dayfinggg/openai-codex-agent-skills.git -
FsLangMCP
MCP serversSemantic F# for AI coding agents (Claude Code · Cursor · Copilot · Codex) — an MCP server that gives LLMs real FCS/FSAC compiler intelligence (find, check, types, rename) instead of grepping F#.
git clone https://github.com/Neftedollar/FsLangMCP.git -
agent-skills
SkillsRemoet agent skills (agentskills.io). One SKILL.md served to Hermes, OpenClaw, and any MCP-capable harness.
git clone https://github.com/remoet-labs/agent-skills.git -
skills
SkillsA plugin of cross-agent skills for AI coding agents — GitHub Copilot, Claude, and Codex — installable with the skills CLI (npx skills add). Includes create-canvas-kit for building Copilot canvas extensions.
git clone https://github.com/jongio/skills.git -
ios-agent-skill
SkillsSwift source, Apple guides and MCP tools for AI coding agents. Review iOS code, scaffold apps, and build/run/preview with Xcode Simulator.
git clone https://github.com/Nagarjuna2997/ios-agent-skill.git -
flint
SkillsFlint · local-skills-hub — a local-first personal AI skills asset manager. Centralize, tag, deduplicate skills, and deploy them into agent and project directories via symlink/copy. Your files, your assets — never locked in.
git clone https://github.com/lcy362/flint.git -
AgentHydra
MCP serversEvery local AI coding session in one tab: Claude Code, Codex and OpenCode in a single list, with a queue you can schedule and isolated Claude Desktop instances kept apart. Local, private, MCP-native.
git clone https://github.com/LunarWerxs/AgentHydra.git -
awesome-ai-agents
MCP serversCurated list of AI agent frameworks, coding and automation agents, MCP servers, and evaluation tools.
git clone https://github.com/frangelbarrera/awesome-ai-agents.git -
spring-ai-playground
AI repositoriesSafe local execution layer for AI agent tools. Build and test-run MCP tools (no pass, no run), serve them from a built-in MCP server, and use them in Agentic Chat with RAG, human-in-the-loop approval, and built-in observability. Cross-platform desktop app powered by Spring AI.
git clone https://github.com/spring-ai-community/spring-ai-playground.git -
willdeep-cli
Agents & frameworks自托管 AI Coding Agent(Rust):常驻 Runtime 撑起终端 / 浏览器 / 手机三端;每行改动可追溯到具体 Agent 与工具调用,子 Agent 的活由退出码裁决,检查点回退、目标 token 预算与验收清单跨轮次跨重启累计,用量与反馈账本留在本地。接任意 OpenAI 兼容或 Anthropic 端点。Self-hosted auditable AI coding agent: per-line attribution, exit-code-verified sub-agents, restart-safe goal budgets, local usage and feedback ledgers.
git clone https://github.com/niuwoai/willdeep-cli.git -
hadron
MCP serversA native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an automatic merge gate.
git clone https://github.com/s0lda/hadron.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.