# Human approval and handoff for AI agents

> 7 human approval & handoff listings ranked by the Anchor benchmark. Leader Temporal (BB). Services that pause an agent to ask a person: approve an action, answer a question or take over a task, over Slack, email or a web inbox, then resume the agent with the answer. Compared on channels, routing, timeouts and audit.

- Canonical: https://www.anchorterminal.com/categories/human-in-the-loop
- Markdown: https://www.anchorterminal.com/categories/human-in-the-loop.md (~2,750 tokens)
- Slim: https://www.anchorterminal.com/categories/human-in-the-loop.min.md (~430 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/categories/human-in-the-loop.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

Services that pause an agent to ask a person: approve an action, answer a question or take over a task, over Slack, email or a web inbox, then resume the agent with the answer. Compared on channels, routing, timeouts and audit.

- Tools ranked: 7 · agent-ready (BB or better): 2 · accept x402: 0 · hosted endpoints: 6 · desk reviews by the panel: 26
- JSON: https://www.anchorterminal.com/api/v1/tools.json (list) · https://www.anchorterminal.com/api/v1/rankings.json (ranked) · https://www.anchorterminal.com/api/v1/x402.json (payable) · https://www.anchorterminal.com/api/v1/capabilities.json (by capability)
- Grades run AA, A, BB, B, C, D, E, F · methodology: https://www.anchorterminal.com/benchmark/

- Capabilities in this category: hitl.approve, hitl.ask, hitl.handoff, hitl.channels, hitl.audit
- https://letme.dev/hitl.approve picks the top-graded tool in this list and says how to call it direct; calling through letme comes later (https://www.anchorterminal.com/letme/index.md)

## Ranking

| # | Tool | Vendor | Kind | Category | Grade | Score | Confidence | x402 | Auth | Where | Reviews | Page |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 21 | Temporal | Temporal Technologies | Model platform | Human approval | BB | 77.2 | medium | no | OAuth or key | local | 3.6/5 (8) | https://www.anchorterminal.com/tools/temporal.md |
| 46 | Trigger.dev | Trigger.dev | Model platform | Human approval | BB | 74.8 | medium | no | OAuth or key | hosted + local | 3.6/5 (8) | https://www.anchorterminal.com/tools/trigger-dev.md |
| 160 | Inngest | Inngest | Model platform | Human approval | B | 66.3 | medium | no | OAuth or key | hosted | 2.5/5 (2) | https://www.anchorterminal.com/tools/inngest.md |
| 321 | Permit MCP Gateway | Permit.io | Model platform | Human approval | C | 54.5 | medium | no | OAuth | hosted | 2.5/5 (2) | https://www.anchorterminal.com/tools/permit-mcp-gateway.md |
| 327 | Orkes Conductor Human tasks | Orkes | Model platform | Human approval | C | 54.2 | medium | no | API key | hosted + local | 2.5/5 (2) | https://www.anchorterminal.com/tools/orkes-conductor.md |
| 350 | Pushary | Pushary | MCP server | Human approval | D | 51.4 | medium | no | API key | hosted | 2.5/5 (2) | https://www.anchorterminal.com/tools/pushary.md |
| 407 | gotoHuman | gotoHuman | HTTP API | Human approval | E | 43.9 | medium | no | API key | hosted + local | 2/5 (2) | https://www.anchorterminal.com/tools/gotohuman.md |

Scores are from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/), with Performance and Task success pending. p95 latency and context cost come from our probes, which haven't run yet.

## Summaries

### 21. Temporal, BB (77.2)

Open-source durable execution platform with SDKs in Go, Java, Python, TypeScript, .NET, PHP, Ruby and Rust, run yourself or on Temporal Cloud. Waits of any length with a timeout survive worker restarts and deploys. No reviewer inbox, notifications or routing, so the human side is all your code.

- Page: https://www.anchorterminal.com/tools/temporal · Markdown: https://www.anchorterminal.com/tools/temporal.md · JSON: https://www.anchorterminal.com/api/v1/tools/temporal.json
- Capabilities: hitl.approve, hitl.ask, hitl.audit, agent.durable, automation.workflows, automation.code

### 46. Trigger.dev, BB (74.8)

Open-source background jobs and durable tasks in TypeScript. Tokens complete from a backend, a pre-signed callback URL or the browser with a token scoped to one waitpoint. 10-minute default timeout on tokens.

- Page: https://www.anchorterminal.com/tools/trigger-dev · Markdown: https://www.anchorterminal.com/tools/trigger-dev.md · JSON: https://www.anchorterminal.com/api/v1/tools/trigger-dev.json
- Capabilities: hitl.approve, hitl.ask, agent.durable, automation.workflows, automation.code · endpoint: `https://api.trigger.dev`

### 160. Inngest, B (66.3)

Durable execution platform for TypeScript, Python and Go, with event-driven workflows and support for human approval. Waits are durable and cost nothing while suspended, with runs up to 30 days on Free and 366 on Business. No reviewer inbox, Slack app or email, so the human side is your code.

- Page: https://www.anchorterminal.com/tools/inngest · Markdown: https://www.anchorterminal.com/tools/inngest.md · JSON: https://www.anchorterminal.com/api/v1/tools/inngest.json
- Capabilities: hitl.approve, hitl.ask, agent.durable, automation.workflows, automation.code · endpoint: `https://inn.gs/e/`

### 321. Permit MCP Gateway, C (54.5)

Hosted proxy between MCP clients and MCP servers that signs in the human behind the agent, checks each tool call against Permit.io policy and logs it. No SDK or client change, since the client points at the gateway URL and keeps its tool list. Approvals are Enterprise only, through a demo, with no published price.

- Page: https://www.anchorterminal.com/tools/permit-mcp-gateway · Markdown: https://www.anchorterminal.com/tools/permit-mcp-gateway.md · JSON: https://www.anchorterminal.com/api/v1/tools/permit-mcp-gateway.json
- Capabilities: hitl.approve, hitl.channels, hitl.audit, auth.oauth, auth.consent, auth.agent-identity, auth.audit · endpoint: `https://{subdomain}.agent.security/mcp`

### 327. Orkes Conductor Human tasks, C (54.2)

Workflow orchestration platform, built on the open-source Conductor, with a Human task that pauses a workflow, assigns a form to a user or group and resumes with the submitted answer. Escalation chains with a time limit per assignee and a choice of leaving the task open or failing the workflow. No built-in Slack or email prompt, so alerts need a trigger policy and a second workflow.

- Page: https://www.anchorterminal.com/tools/orkes-conductor · Markdown: https://www.anchorterminal.com/tools/orkes-conductor.md · JSON: https://www.anchorterminal.com/api/v1/tools/orkes-conductor.json
- Capabilities: hitl.approve, hitl.ask, hitl.handoff, hitl.audit, agent.durable, automation.workflows · endpoint: `https://developer.orkescloud.com/api`

### 350. Pushary, D (51.4)

Hosted MCP server that lets a coding agent notify you and ask you a yes or no, multiple-choice or free-text question on your phone, Mac, Slack or browser, then wait for the answer. Six small tools with a detailed skill that says when to ask, when to notify and when to stay quiet. No free plan, and the 3-day trial takes a card up front.

- Page: https://www.anchorterminal.com/tools/pushary · Markdown: https://www.anchorterminal.com/tools/pushary.md · JSON: https://www.anchorterminal.com/api/v1/tools/pushary.json
- Capabilities: hitl.approve, hitl.ask, hitl.channels, hitl.audit, notify.push · endpoint: `https://pushary.com/api/mcp/mcp`

### 407. gotoHuman, E (43.9)

Hosted review inbox for AI agents. Built for agent review, with TypeScript and Python SDKs, a 3-tool MCP server, an n8n node and a Make app. No status page, published rate limits or documented error responses.

- Page: https://www.anchorterminal.com/tools/gotohuman · Markdown: https://www.anchorterminal.com/tools/gotohuman.md · JSON: https://www.anchorterminal.com/api/v1/tools/gotohuman.json
- Capabilities: hitl.approve, hitl.ask, hitl.channels, hitl.audit · endpoint: `https://api.gotohuman.com`

## How we test this category

An agent asks for approval of a risky action over two channels and gets one approval, one rejection and one timeout. We check the routing, what the approver sees, how the answer reaches the agent and what is logged. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.

## Indexed, not reviewed (12)

Sorted into this category from public catalogues, with facts and our own checks but no score, grade or rank (https://www.anchorterminal.com/indexed/index.md).

| Listing | Kind | What it does | Why it's here |
| --- | --- | --- | --- |
| [abs-mcp](https://www.anchorterminal.com/tools/ausdata-abs-mcp.md) | MCP server | Query the ABS in plain English — CPI, labour force, building approvals, migration, GDP. | vendor's own |
| [Adako: ad ops for AI assistants](https://www.anchorterminal.com/tools/adako-ads.md) | MCP server | Google, Meta, LinkedIn and ChatGPT Ads for AI assistants. Every change needs your approval. | vendor's own |
| [agentimus](https://www.anchorterminal.com/tools/heera-agentimus.md) | MCP server | heera.it via Agentimus: AI readiness, traffic, request log, search & index reports, by approval. | vendor's own |
| [bvcc-agent-wallet](https://www.anchorterminal.com/tools/blockventurechaincapital-bvcc-agent-wallet.md) | MCP server | Non-custodial BVCC Agent Wallet on-chain for AI agents: balances, transfers, approvals, swaps. | vendor's own |
| [Clize](https://www.anchorterminal.com/tools/clize.md) | MCP server | Real-world actions for AI coding agents: an inbox with approval outbox, deploys, domains, payments. | vendor's own |
| [Elicitly](https://www.anchorterminal.com/tools/elicitly.md) | MCP server | Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor | vendor's own |
| [Lassare](https://www.anchorterminal.com/tools/lassare-ask.md) | MCP server | Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack. | vendor's own |
| [logi-approval](https://www.anchorterminal.com/tools/1pass-logi-approval.md) | MCP server | logi Agent Approval Gate — human approval on the phone before high-risk agent actions. | vendor's own |
| [monnet.ai MCP server](https://www.anchorterminal.com/tools/monnet-mcp.md) | MCP server | MCP server for Monnet — motions, plans, files, approvals, and the team's company brain. | vendor's own |
| [Proof Holdings](https://www.anchorterminal.com/tools/proof-mcp-server.md) | MCP server | One API, all things verified — control, delegation, human approval, anti-impersonation. | vendor's own |
| [Selda](https://www.anchorterminal.com/tools/selda.md) | MCP server | Find customers, research each one and draft the outreach. Nothing sends without approval. | vendor's own |
| [Social Champ](https://www.anchorterminal.com/tools/socialchamp-mcp.md) | MCP server | Connect AI agents to Social Champ: manage channels, posts, AI content, queue, and approvals. | vendor's own |