Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
MCP CPG Human in the Loop (HITL)
MCP serversNavigator for BPC Agentic Procurement
-
AutoSwarm-Shadow-Adapter
AI repositoriesZero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.
git clone https://github.com/AhmadHassan-BTed/AutoSwarm-Shadow-Adapter.git -
pneumaticworkflow
Tools & appsFree and source-available Apache 2.0 licensed lightweight workflow automation tool.
git clone https://github.com/pneumaticapp/pneumaticworkflow.git -
grok-bot-architecture
Agents & frameworksMCP-native multi-agent architecture with desktop agents and human-in-the-loop gates
git clone https://github.com/tiagovilasboas/grok-bot-architecture.git -
aerial-autonomy-stack
Agents & frameworksAn open harness to simulate and deploy PX4/ArduPilot/Betaflight perception-based drone swarms with ROS2, YOLO, NVIDIA Jetson
git clone https://github.com/JacopoPan/aerial-autonomy-stack.git -
e2a — email for AI agents
MCP serversAuthenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified.
-
workflowbuilder
Tools & appsWorkflow orchestration framework for your product, open source: a white-label React workflow builder, durable execution on your own Temporal, human approval steps for AI agents, and a live view of every run.
git clone https://github.com/synergycodes/workflowbuilder.git -
AgentChat
SkillsAgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。
git clone https://github.com/Shy2593666979/AgentChat.git -
meridian
MCP serversPersistent memory, task coordination, and HITL queue for AI coding sessions.
@meridianmcp/mcp@1.0.2 -
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 -
ShadowCrawl
MCP serversStealth scraping & search. Bypasses Cloudflare, DataDome & LinkedIn via Cyborg HITL approach.
-
ShadowCrawl
MCP serversRust MCP stealth scraper: anti-bot search/scrape with CDP fallback + HITL non-robot.
-
envault
MCP serversSecure secret management with a Human-In-The-Loop (HITL) interceptor for agent mutations.
@dinanathdash/envault-mcp-server@1.12.0 -
Obsidian Turbocharged
MCP serversGoverned Obsidian vault access: hybrid retrieval, Markdown-native memory, HITL confirmations.
obsidian-tc@1.34.0 -
nexus-browser-mcp
MCP serversEvent-driven deterministic browser MCP: HITL gates, audit, console/network/perf observability.
nexus-browser-mcp@0.3.0 -
mcp-relay
MCP serversRunRelay MCP relay — AI agent threads, HITL confirmations, and travel capability discovery.
-
Reliquary-TC
MCP serversGoverned Obsidian vault access: hybrid retrieval, Markdown-native memory, HITL confirmations.
reliquary-tc@2.0.1 -
chp-mcp
MCP serversSpend approval gate for AI agents: budget caps, HITL thresholds, signed audit hash.
@cubiczan/chp-mcp@0.1.2 -
Cordon for MCP
MCP serversCordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.
@getcordon/cli@0.3.0 -
danao 智能组织大脑
MCP serversGoverned autonomous-agent platform: HITL approvals, budget gates, audit chain, effect ledger.
-
SIGNALS Loyalty Agent Platform
MCP servers63 MCP tools for loyalty programs, rewards, and member operations with HITL approval.
-
hedera-mcp-platform
MCP serversHedera ecosystem intelligence for AI agents. 29 tools, pay per call in HBAR. HITL enforced.
hedera-mcp-platform@2.2.1 -
py-idp
AI repositoriesAI-enabled Intelligent Document Processing for Python: 12+ LLM backends, Pydantic schemas, self-hosted OCR (Nanonets-OCR2-3B), auto-schema discovery, HITL review, prod FastAPI server. AGPL-3.0 + commercial.
git clone https://github.com/rollroyces/py-idp.git -
e2a — email for AI agents
MCP serversAuthenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified.
@e2a/mcp-server@0.3.2
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.