Human Approval
Pausing agents for a person to approve risky actions. As of 2026-11-21, 270 indexed products offer it (77 with full profiles), in 10 forms: 235 MCP servers, 8 Agent skills, 6 Infrastructure, 6 Libraries. 135 were published in the last 90 days, against 72 in the 90 days before. LangGraph has the most GitHub stars, 47% of the total across 203 products with their own repository.
CapabilitySegment label: Crowded, slowing DER
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 235 indexed · 47 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | daguSelf-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler. | dagucloud | 4.6k | today | ||
| 2 | heymBuild 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. | heymrun | 1.8k | today | ||
| 3 | free4chatTemporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace. | i365dev | 1.2k | 4d ago | ||
| 4 | northcinderOpen-source MCP server for comparing products and asking the buyer before purchase. | cinderline | 1.2k | 3mo ago | ||
| 5 | mcp-client-for-ollamaHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences. | jonigl | 837 | 2d ago | ||
| 6 | CambiumGovernance standard and reference toolset for LLM-maintained knowledge corpora | KimGLee | 664 | 2mo ago | ||
| 7 | mcpAuthorize consequential AI agent actions before execution | decionis.com | 661 | today | ||
| 8 | mcp-ssh-managerSSH for AI agents: commands, files, backups and health, with approval, a vault and an audit trail | bvisible | 546 | today | ||
| 9 | cordumThe action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence. | cordum-io | 507 | 2d ago | ||
| 10 | HyphaHarness-oriented agent system framework for production-grade LLM agent applications | CodeSoul-co | 452 | 6d ago |
Agent skills 8 indexed · 8 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | hiveMulti-Agent Harness for Production AI | aden-hive | 11k | 4d ago | ||
| 2 | Deep-Research-skillsStructured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control | Weizhena | 2.6k | 3mo ago | ||
| 3 | qualitylayerPlan, implement and verify software with your favorite coding agents. Work in the App or browser, or in your own terminal, IDE or agent app. | maxritter | 2.2k | today | ||
| 4 | solo-to-team-skillsHuman-led MAS toolkit: 16 roles, 6 group templates, four platform bundles, evidence-based review and handoff. 一人成队:一个人统筹多智能体协作。 | dabingfy-dot | 1.1k | 4d ago | ||
| 5 | digital-marketing-proAn open-source AI based digital marketing operating system for strategy, SEO, AEO/GEO, paid media, content, CRM, and analytics - grounded in brand context, human approval, and verifiable outputs. Best for Brands, Agencies and one person campanies. | indranilbanerjee | 978 | 14d ago | ||
| 6 | AgentChatAgentChat 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。 | Shy2593666979 | 935 | 1mo ago | ||
| 7 | langgraphExpert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. | sickn33 | — | 1d ago | ||
| 8 | autonomous-agent-patternsDesign patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants. | davila7 | — | today |
Infrastructure 6 indexed · 6 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | intelligent-audit-systemAuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery. | Ricky-7-Yan | 1.2k | 16d ago | ||
| 2 | AegisRuntime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes. | Justin0504 | 524 | 21d ago | ||
| 3 | exxpertsA free, open-source desktop app for getting work done with AI. It shows you what it would remember before it saves anything. | EXXETA | 465 | 4d ago | ||
| 4 | ai-decision-systemReplayable, offline-verifiable records for AI-assisted go/no-go decisions: typed model answers, policy-gated approvals, A/B ship gates, release gates. | BichengWang | 358 | 1d ago | ||
| 5 | continuumContinuum — the agent runtime by ShyftLabs. Build, orchestrate, ship. | shyftlabs | 85 | 1mo ago | ||
| 6 | evestackThe whole eve stack. On your own machine. Durable Postgres sessions, a Docker sandbox, memory, approvals, schedules, 1,070 tool integrations, and a dashboard that drives the agent. | SammyTourani | 18 | 1d ago |
Libraries 6 indexed · 3 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | red-team-blue-team-agent-fabricAI agent security harness, adversarial testing: 661 executable tests in the v4.31.1 release, across MCP, A2A, x402/L402, decision governance, benchmark integrity, human-in-the-loop, skill supply chain. Five target shapes: a verdict must be able to be wrong AND to be right. OWASP Agentic v1.1 T1-T17, AIUC-1 crosswalk (2026-10-15), NIST AI 800-2. | msaleme | 34 | today | ||
| 2 | hybroThe open interoperability layer for AI agents. Connect your favorite agents / harnesses and robots. Work together. | hybroai | 20 | today | ||
| 3 | vokoLocal-first Agent communication runtime and gateway for A2A, MCP, E2EE messaging, REST/Webhook, and multi-agent collaboration. | laoyudashu | 18 | 8d ago |
Plugins 5 indexed · 4 profiled
4 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | reinsStop AI agents from doing things you didn't ask for. | pegasi-ai | 394 | 1mo ago | ||
| 2 | m5-paper-buddy📟 Claude Code physical companion on M5Paper V1.1 e-ink. Multi-session dashboard, hardware approval (buttons + touch), AskUserQuestion option cards, CJK, USB/BLE, installable as a Claude Code plugin. / Claude Code 实体搭档,把 M5Paper 变成 Claude Code 的多会话看板 + 硬件审批面板。 | op7418 | 166 | 7mo ago | ||
| 3 | anti-vibe-writingMake AI writing sound human, in English and 中文. A Claude Code / Codex / any-agent skill that strips templated phrasing, consultant-speak, markdown clutter, em-dashes, and copy-paste model residue while keeping the meaning. | weijt606 | 136 | 6d ago | ||
| 4 | reviewer-author-loopHuman-in-the-loop manuscript improvement workflow that cycles through reviewer critique, author revision, verification, and re-review until acceptance or a pause condition. | ccplugins | — | 3mo ago |
Frameworks 4 indexed · 4 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | LangGraphLow-level orchestration framework that models agents as stateful graphs with checkpointing, human-in-the-loop interrupts and durable execution. | LangChain | 45k | today | ||
| 2 | Deuz-SDKTypeScript 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. | Deuz-AI | 508 | 1mo ago | ||
| 3 | SicoAn open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets. | microsoft | 284 | 1d ago | ||
| 4 | fullstack-langgraph-nextjs-agent Production-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynamic tool loading, human-in-the-loop tool approval, persistent conversation memory with PostgreSQL, and real-time streaming responses. Built with TypeScript, React, Prisma, and Tailwind CSS. | agentailor | 135 | 2mo ago |
Agent projects 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | SoduWorkThe AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted. | mdiri-ai | 6.2k | today | ||
| 2 | LoopForgeSelf-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows for coding assistants. | Tencent | 5.4k | today |
Rules packs 2 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | aria-knowledgeApplied reasoning, persistent agent memory, context engineering, and human-governed trust for AI coding agents — Claude Code, Claude Cowork, Codex, Cursor, Antigravity. Compatible with Obsidian. | mikeprasad | 19 | 3d ago |
Automation platforms 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Relay.appWorkflow automation tool with AI steps and human-in-the-loop approvals inside multi-step app integrations. | Relay | — | — |
SaaS products 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Auth0 for AI AgentsIdentity features for agents: user authentication, Token Vault for calling third-party APIs on a user behalf, async human approval and fine-grained authorisation for RAG. | Okta (Auth0) | 16 | 3d ago |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 235 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 8 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Claude Code | 5 |
| Codex | 4 |
| Cursor | 2 |
| Google Antigravity | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| Kubernetes | 4 | 1.5% |
| PostgreSQL | 3 | 1.1% |
| Telegram | 3 | 1.1% |
| Obsidian | 2 | 0.7% |
| 2 | 0.7% | |
| Android | 1 | 0.4% |
| Confluence | 1 | 0.4% |
| Discord | 1 | 0.4% |
| Elasticsearch | 1 | 0.4% |
| Ethereum | 1 | 0.4% |
| GitHub | 1 | 0.4% |
| Gmail | 1 | 0.4% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| human approval | 86 |
| human in the loop | 116 |
| human-in-the-loop | 45 |
| approval workflow | 5 |
| require approval | 0 |
| manual approval | 0 |
| hitl | 18 |
Segment statistics
Whole catalogue (270 indexed products). Calculated 2026-11-21.
Crowded, slowing. Among the largest fifth of capabilities, but its launches grew more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.251 means stars are spread as if across about 4 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .