Library
86,235 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 build an AI agent
-
better-agentic-ide
SkillsBetter Agentic Development Environment
git clone https://github.com/alvin-reyes/better-agentic-ide.git -
tinystruct
Agents & frameworksA lightweight, modular Java application framework for web and CLI development, designed for AI integration and plugin-based architecture. Enabling developers to create robust solutions with ease for building efficient and scalable applications.
git clone https://github.com/tinystruct/tinystruct.git -
resonance
SkillsOperator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.
git clone https://github.com/manusco/resonance.git -
claude-remotion-skill
SkillsOpen-source Claude agent skill that teaches Claude Code, Claude Desktop & Claude AI to create and edit professional motion graphics videos with Remotion. AI video editing, B-roll, captions, sound design — from one prompt.
git clone https://github.com/haidrrrry/claude-remotion-skill.git -
agentic-ai
AI repositoriesAgentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.
git clone https://github.com/mahmoudrabie/agentic-ai.git -
vibeframe
Tools & appsFrontier AI video generation for coding agents - Seedance, Runway, Veo, Kling on your own keys, behind a hard cost cap. CLI + MCP.
git clone https://github.com/vericontext/vibeframe.git -
orchestkit
AI repositoriesOrchestKit: free and open source skills and agents for Claude Code, Cursor, Codex and five more coding agents, plus hooks in Claude Code. 116 skills, 36 agents, 163 hooks. Install `ork` for stable (v10.x).
git clone https://github.com/yonatangross/orchestkit.git -
squads-cli
Agents & frameworksCLI for managing AI agent squads. Status, memory, goals, feedback, and dashboard for your autonomous agents.
git clone https://github.com/agents-squads/squads-cli.git -
AI-Interview
Agents & frameworks开源的 AI 模拟面试系统:真人数字人面试官开口提问、按你的回答追问,报告逐题打分;另含 Docker 判题笔试与 AI 简历优化。Java 21 + Spring AI Alibaba + Vue 3。
git clone https://github.com/xgwangdl/AI-Interview.git -
gflow-cli
AI repositoriesDrive Google Flow from the command line: Veo video and Imagen images, scripted, batched and pipeline-ready. Ships an MCP server so coding agents can drive it too, giving you and your agents full programmatic control over generation. Unofficial, alpha, not affiliated with Google.
git clone https://github.com/ffroliva/gflow-cli.git -
lucid-memory
AI repositoriesMemory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG. Finds what RAG misses. Zero cloud, zero cost.
git clone https://github.com/JasonDocton/lucid-memory.git -
medulla
Agents & frameworksManage upto 1000 agents using automations and workflows
git clone https://github.com/tinyhumansai/medulla.git -
data-agent-tutorial
AI repositoriesData-Agent:从 0 到 1 构建 Text2SQL 智能体实战教程,覆盖 StateGraph 编排、双重 RAG、关系图谱、HITL 人工确认、SQL 自动纠错、Python Docker 沙盒执行与 A2A + SSE 流式交互。
git clone https://github.com/qifan777/data-agent-tutorial.git -
boring-is-all-you-need
Tools & appsBoring Is All You Need: a Codex Desktop workflow replacement with transactional migration, audit-only managed hooks, risk-based review, scoped checkpoint commits, and release evidence.
git clone https://github.com/Khalilzhang0825/boring-is-all-you-need.git -
bambu-studio-ai
SkillsBambu Lab AI (Bambu Studio AI): agent skill for 3D printing on Bambu Lab. Finds models on MakerWorld & Printables, generates or designs them in CAD, checks printability, hands them to Bambu Studio and reads printer/AMS status. For Claude Code, Codex, Cursor, Gemini CLI and any SKILL.md agent. Featured in 我的拓竹 Skill 大赏.
git clone https://github.com/heyixuan2/bambu-studio-ai.git -
token-optimizer-mcp
Tools & apps91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
git clone https://github.com/ooples/token-optimizer-mcp.git -
kyb
MCP serversGit-backed shared memory for AI agent fleets: searchable knowledge base, incident and task tracking, every write versioned and attributed. CLI, HTTP API and MCP server.
git clone https://github.com/alex09x/kyb.git -
okto-pulse
MCP serversLocal-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.
git clone https://github.com/OktoLabsAI/okto-pulse.git -
omnistack-agent
PromptsPlatform-agnostic AI agent: one Full-Stack Software Engineer brain, compiled into ready-to-paste adapters for ChatGPT, Claude, Copilot, Gemini & Cursor. Zero-dependency, MIT.
git clone https://github.com/Ricar66/omnistack-agent.git -
AgentRecall-X
MCP serversCorrection-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
git clone https://github.com/Goldentrii/AgentRecall-X.git -
uncomment
Tools & appsFast, AST-accurate comment removal and tag-comment linting for 300+ languages, built on tree-sitter. CLI, GitHub Action, pre-commit hooks and agent plugins.
git clone https://github.com/polylint/uncomment.git -
loop.js
Agents & frameworksA loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.
git clone https://github.com/loop-js/loop.js.git -
LAP
Tools & appsYour agents are guessing at APIs. Give them the actual Agent-Native spec. 1500+ API's Ready To-Use skills, Compile any API spec into a lean, agent-native format. 10× smaller. OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman.
git clone https://github.com/Lap-Platform/LAP.git -
deskrpg
Agents & frameworksSelf-hosted 3D virtual office for Hermes Agent — your profiles become AI employees who sit at desks, chat, hold meetings, work kanban cards and run cron jobs, while your team shares the office in real time.
git clone https://github.com/dandacompany/deskrpg.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.