Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
mateclaw
Agents & frameworks🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.
git clone https://github.com/mateaix/mateclaw.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 -
loop-me
SkillsGrill me about specs for the workflows I want to build, within this workspace.
-
Deep-Research-skills
SkillsStructured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control
git clone https://github.com/Weizhena/Deep-Research-skills.git -
Deuz-SDK
Agents & frameworksTypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemini, Grok, DeepSeek, Ollama. Node, Bun, Deno, edge.
git clone https://github.com/Deuz-AI/Deuz-SDK.git -
loophole tape: Solana token safety
MCP serversSolana token safety and pump.fun rug checks: free for any mint, paid depth in USDC on Solana or Base
https://github.com/gosadu/loophole-tape/releases/download/mcp-v0.2.0/loopholetape-mcp-0.2.0.mcpb@0.2.0 -
Frontend Design Loop MCP
MCP serversDesign-first MCP for coding agents that improves websites with screenshot-grounded iteration.
frontend-design-loop-mcp@1.0.0 -
clay
Agents & frameworksA self-hosted workspace where people and coding agents work together across projects, sessions, and providers.
git clone https://github.com/chadbyte/clay.git -
Hypha
Agents & frameworksHarness-oriented agent system framework for production-grade LLM agent applications
git clone https://github.com/CodeSoul-co/Hypha.git -
dsh-agent-team
Agents & frameworksdsh-agent-team: Agent Teams for DeepSeek Harness. Hand work to a team of agents that carries it end to end while you set the direction and hold the gates. You stay on the loop, and step back in whenever you want.
git clone https://github.com/Contexera/dsh-agent-team.git -
GraphCode
Agents & frameworksGraph Engineering, simplified — with GraphCode. #graphcode
git clone https://github.com/scgopi/GraphCode.git -
Pushary: human-in-the-loop for AI agents
MCP serversHuman-in-the-loop for AI agents: ask a person and get approvals or answers by push notification.
-
Inside the Loop
MCP serversVerified latest versions, changes and exact-error fixes for agent dev tools. Read-only.
-
heym
MCP serversBuild agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.
git clone https://github.com/heymrun/heym.git -
Followable agent result pages + human-in-the-loop yes/no approval gates before irreversible actions.
-
Check many URLs at once: HTTP status, redirect chains and loops, so you see which links break.
-
awaken
Agents & frameworksAI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.
git clone https://github.com/awakenworks/awaken.git -
loophole-tape
MCP serverspump.fun & Robinhood Chain launch data: radar, risk checks, delta feed, datasets, keys. x402 USDC
-
paperthin
SkillsThe skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.
git clone https://github.com/LilMGenius/paperthin.git -
idd-skill
Skills🤖 An automated setup kit for implementing loop engineering based on issue-driven development in your repository; since 2026.5
git clone https://github.com/kurone-kito/idd-skill.git -
Deep Learning Loop
Prompts# Deep Learning Loop System v1.0 > Role: A "Deep Learning Collaborative Mentor" proficient in Cognitive Psychology and Incremental Reading > Core Mission: Transform complex knowledge into long-term memory and…
-
BPJ Task Loop
MCP serversBPJ rule-based task-state reviews and workflow tool discovery. Free, no account required.
-
loopback
MCP serversFeedback bus for coding agents: pin feedback on the app you're building; a fix turns the pin green
loopback-mcp-server@0.9.4 -
GameDesignOS
Tools & appsLocal-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.
git clone https://github.com/DY-2026/GameDesignOS.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.