Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
krusch-context-mcp
MCP serversLong-term memory for AI coding agents — remembers project rules across sessions at $0 AI cost (MCP server, SQLite/PostgreSQL). 90.26% on Snap LoCoMo.
git clone https://github.com/kruschdev/krusch-context-mcp.git -
System prompts for using AI tools to generate and improve system prompts
git clone https://github.com/danielrosehill/System-Prompt-Generation-Configurations.git -
skills
SkillsSkills to augment LLM thinking process, integrated with InfraNodus insight generation tool
git clone https://github.com/infranodus/skills.git -
EAC-design-world
MCP serversDeepSeek Harness 本地视频制作与设计插件:多轨剪辑、模板与设计体系、原生预览画布和真实文件导出
git clone https://github.com/Ebony-Vinyl/EAC-design-world.git -
moira
MCP serversAgent Workflow Engine for AI agents over MCP — per-step directives, completion conditions, and JSON-Schema validation. Self-hostable (Apache-2.0).
git clone https://github.com/moira-mcp/moira.git -
AlysisCode
Tools & appsAlysis AI — one desktop app for building software with Alysis Code, creating documents with Alysis Work, and delegating ongoing tasks to Alysis Owls.
git clone https://github.com/AlysisAi/AlysisCode.git -
GitHub-Copilot-app
PromptsThe GitHub Copilot app is an agent-native desktop experience for finding, running, steering, and landing software work across your GitHub repositories.
git clone https://github.com/PowerTestingHut/GitHub-Copilot-app.git -
ai-research-skills
SkillsUniversal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.
git clone https://github.com/WenyuChiou/ai-research-skills.git -
claude-ops-inspector
Agents & frameworksSubagent Verification for Claude AI Code Networks 2026
git clone https://github.com/minetechnic2012-lang/claude-ops-inspector.git -
llm-bulls-and-cows-benchmark
Datasets & benchmarksA mini-framework for evaluating LLM performance on the Bulls and Cows number guessing game, supporting multiple LLM providers.
git clone https://github.com/stalkermustang/llm-bulls-and-cows-benchmark.git -
Kimi-K3.1-Pro-pruned75
Modelsimage text to text model by vllm-project · transformers
vllm-project/Kimi-K3.1-Pro-pruned75 -
ai-agent-engineer-handbook
PromptsAI Agent / LLM 应用工程师面试与学习手册 | 中文 / English
git clone https://github.com/harrisliangsu/ai-agent-engineer-handbook.git -
liki
MCP serversLiki — 专业命理 Skill:天文历算引擎排盘,断语附经典出处,结论可验证。八字 · 紫微 · 六爻 · 奇门 · 黄历择日 · 风水 · 起名 | Liki — Professional Skill for Chinese Metaphysics: astronomical-engine charting, classically-sourced judgments, verifiable conclusions. BaZi · ZiWei · Liuyao · QiMen · Date Selection · Feng Shui · Naming.
git clone https://github.com/ml8s/liki.git -
google-analytics-mcp
MCP serversGoogle Analytics 4 data to AI agents, agentic workflows, and MCP clients. Give agents analysis-ready access to website traffic, user behavior, and performance data with schema discovery, server-side aggregation, and safe defaults that reduce data wrangling.
git clone https://github.com/surendranb/google-analytics-mcp.git -
Qwen3.8-27B-S-mirai-GGUF
Modelstext generation model by alesha-pro
alesha-pro/Qwen3.8-27B-S-mirai-GGUF -
HIG Doctor
MCP serversApple Human Interface Guidelines search, lookup, and project audits for AI coding agents.
hig-mcp@0.2.3 -
runx
Skillsthe governed runtime for agent skill workflows, off the leash but on the record
git clone https://github.com/runxhq/runx.git -
aios
Agents & frameworksAmplify yourself and your team – with AI co-workers.
git clone https://github.com/The-AIOS/aios.git -
domscribe
Tools & appsDomscribe is a pixel-to-code development tool that bridges the gap between running web applications and their source code.
git clone https://github.com/patchorbit/domscribe.git -
agent-jev
Agents & frameworksAgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.
git clone https://github.com/malevrigns/agent-jev.git -
familywell
MCP serversThe family organizer for the people you live with: shopping lists, to-dos, calendar, spending, projects, recipes and more. Self-hostable, modular Laravel + React PWA with an MCP server for AI assistants. Free for personal use.
git clone https://github.com/bvdr/familywell.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 -
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 -
lightning
Tools & appsLightning ⚡️ is latest version of the OpenFn platform, a DPG and DPI building block that governments use to manage complex service/workflow automation and data integration projects.
git clone https://github.com/OpenFn/lightning.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.