Looking for HumanLayer's approvals API?
As of 2026-09-02, HumanLayer's site sells coding tools. If you came here for an API that pauses an agent's dangerous tool calls until a human decides, that is the thing Anlyon does.
A few lines on your server, then connect a user.
The jobs it did08
- 01Let the user your agent acts for say yes
- 02Pause a dangerous function until a human says yes
- 03Get told when something is waiting
- 04Require more than one approver
- 05Stop the agent approving its own work
- 06Prove to someone what was decided
- 07Keep the credential out of the agent entirely
- 08Stop the agent without a deploy
An approvals API that moved on leaves your agent's riskiest calls without a gate. Anlyon holds those calls for a yes, from the user your agent acts for or from your team, and sends the exact request that was approved.
What happened
What actually happened
HumanLayer built a human-in-the-loop approvals API for AI agents. It was a good product.
As of our last check, humanlayer.dev sells a multiplayer coding agent workspace: an IDE and cloud platform for running agent sessions, design review, and multi-repo work. The approvals API is no longer the product on the front page.
That is a pivot, not a shutdown. If what they ship today does what you need, keep using it. This page is for people who wanted the approvals product and found an IDE.
Checked 2026-09-02 · humanlayer.dev
Job by job
What you probably came here for
Each of these is a thing the approvals API was used for, and how Anlyon does it today.
| The job | How Anlyon does it |
|---|---|
Let the user your agent acts for say yes | On a call for one of your users, the approval waits for that user. Render |
Pause a dangerous function until a human says yes | Wrap the function in |
Get told when something is waiting | Approval requests notify over Slack, email, Discord, or a webhook. A pending approval stays in the inbox until it is decided or it expires. |
Require more than one approver | Approval policies support N-of-M. A rule can require N distinct approvers before the call runs. N counts distinct credentials for API-key deciders and distinct users for dashboard and OAuth deciders. Admins, members and approvers can decide, and a viewer cannot. A member can hold a different role in each environment, such as approver in production only. The dashboard shows the progress and which policy required it. |
Stop the agent approving its own work | Deciding needs a separate |
Prove to someone what was decided | Every decision records the decider, the timestamp, the note, and the governing policy version, on the same trace as the rest of the run. Traces export as OpenTelemetry JSON, so the record leaves in a standard format. |
Keep the credential out of the agent entirely | This is the part a wrapper cannot do. Define the call as an action once, with the key referenced as |
Stop the agent without a deploy | Halting an environment stops the agent acting and stops anything leaving. Action invocations block, and an already-approved call does not run. Resume, and work picks up where it stopped. |
Swap the wrapper. The drop-in
No framework change. The function your agent calls is the same function, now with a decision in front of it and a record behind it. Your process still runs it with your credential. When you want the key out of the agent too, move the call into an action and invoke it by name.
import { Client } from '@anlyonhq/sdk';const client = new Client({ apiKey: process.env.ANLYON_API_KEY! });// Wrap the function you already have.const refund = client.approvals.gate( { title: 'Refund a customer?', timeoutMs: 10 * 60_000 }, async (orderId: string, amount: number) => stripe.refunds.create({ payment_intent: orderId, amount: Math.round(amount * 100), }),);// Creates an approval, waits for a human, then runs, or throws.await refund('ord_42', 129.99);Already in your stack
If your platform already has an approval switch
Some agent platforms now ship their own approval switch. Here is where that is enough.
OpenAI Agents API
As of 2026-09-30, OpenAI's Agents API and Responses API can pause an MCP tool call for approval. The pause is answered by your own code. Anlyon routes the call to a named reviewer, executes the reviewed request with credentials bound to that action, and records the outcome. Use OpenAI's switch when one developer is the reviewer. Use Anlyon when a second person, a record, or a second agent runtime is involved.
Checked 2026-09-30 · Responses API MCP tool, Agents API MCP connections
Other comparisons
Every statement about another product carries the date it was checked and the page it was read from. If one has gone stale, tell us at support@anlyon.com.
- Agent auth platforms compared, 2026Nine options on tokens, per-user limits, approvals, receipts and erase
- Acting for your users: Arcade, Composio and AnlyonPer-user access, and per-user limits, approvals and receipts
- Nango alternative for AI agentsPer-user OAuth, then a limit and an approval on every write
- Scalekit AgentKit alternativeConnected accounts, connect verification and per-user controls
- Pipedream Connect alternativePer-user rate limits versus per-user limits on writes
- Auth0 Token Vault vs AnlyonWho makes the call, and what a CIBA approval binds to
- Paragon ActionKit alternativeEmbedded integrations versus per-user limits and approvals
- Merge Agent Handler alternativeUser-scoped keys, and limits you set per user
- Human-in-the-loop approval tools for AI agentsFrameworks, policy layers and approval services, dated and sourced
- Anlyon vs building it yourselfFive jobs, and the failure windows behind each one
