Intercept agent tool calls
The Agent Approval Protocol (AAP) sends tool calls to withHuman before execution. The site also lists SDKs for agent frameworks and hooks for coding agents.
withHuman intercepts consequential AI-agent tool calls and applies policy rules or routes them to a human reviewer before execution. It supports agent teams that need review and an audit trail for sensitive actions.
withHuman is an approval layer for AI agents. It intercepts consequential tool calls before they reach the target service, then applies configured rules to approve or deny routine actions or hold requests for human review. Reviewers receive the request context, decide whether to approve it, and the agent continues after an approved call runs. The product is framework-agnostic and offers agent integrations, review channels, escalation paths, and an append-only decision history.
The Agent Approval Protocol (AAP) sends tool calls to withHuman before execution. The site also lists SDKs for agent frameworks and hooks for coding agents.
Rules can evaluate the agent, tool, arguments, and agent context to automatically approve or deny calls, or request human review. Webhooks can connect a policy service; an AI judge is also available for cases rules cannot describe.
Escalation paths assign requests to a team or person, support team escalation order and on-call flows, and can escalate when nobody responds in time.
Approval requests can be delivered through Slack, Discord, email, text message, WhatsApp, and iPhone or Android apps, depending on the plan.
The append-only audit log records requests, decisions, reviewer identity, notes, and request details.
Hold refunds above a configured threshold for a support or payments reviewer while allowing policy-defined routine refunds to proceed automatically.
Require human review for consequential operations such as Kubernetes changes or rolling back a service, with requests directed to the responsible team.
Use policies to review potentially destructive database tool calls or coding-agent actions before they reach their target.
Route an agent's payment or invoice action to an appropriate reviewer, with the tool call and its context available for a decision.
withHuman intercepts the call before it reaches the target service. A pipeline can approve or deny it automatically or hold it for a human decision; an approved call then runs and the agent can continue.
Yes. Approval rules can automatically approve or deny calls based on the agent, tool, arguments, and context. The product also lists an AI judge for calls that rules cannot describe.
The site describes the open Agent Approval Protocol, SDKs for frameworks including LangGraph, CrewAI, and Mastra, and hooks for coding agents such as Claude Code and Codex.
Listed destinations include Slack, Discord, email, text message, WhatsApp, and iPhone and Android apps. Availability varies by plan.
The audit log keeps an append-only history of requests, decisions, reviewer identity, notes, and the request associated with each decision.
Traffic data is for reference only.
| Jul | 0 |
|---|---|
| Aug | 0 |
| Sep | 0 |
Traffic analytics are not available yet.
arcjet.com
Arcjet is an AI agent runtime security platform for inspecting and enforcing policy on agent actions, prompts, tool calls, and data flows. It also protects web and AI endpoints from bots, prompt injection, sensitive-data leaks, and uncontrolled usage.
harden.run
Agentic Integrity Foundation is a local endpoint-security product for coding agents. It evaluates supported tool calls before execution and can allow, approve, make safe, block, or record actions on a developer’s machine.
pushary.com
Pushary Isle is a native Mac app that puts AI agent questions and approval requests in the Mac notch or below the menu bar. It helps people review Claude Code, Codex, Cursor, and other connected agent requests at their desk or answer them from a phone.
usefiretower.com
Firetower is an open-source, self-hosted control plane for running coding agents on servers you own. It lets developers start agent sessions from repositories, monitor them from desktop or mobile clients, review changes, and ship branches without keeping the initiating device online.
deepaksinghcs14.github.io
deadeye is a plugin for coding agents that selects a suitable model and effort level for each task, while trimming verbose command output before it enters context. It is built for Claude Code and also supports Codex CLI, Gemini CLI, Cursor, and Windsurf on an experimental basis.
www.docker.com
Docker MCP Enterprise Gateway governs how MCP-compatible clients access approved servers and tools. It applies identity-aware policy, supplies credentials from an approved secret store, and records tool-call decisions for enterprise teams.
chatvisor.ai
ChatVisor is an AI communication coach for practicing difficult conversations at work, in relationships, sales, and parenting.
aperty.ai
Aperty is an AI portrait editor for natural retouching and batch workflows on Mac and Windows.
visualizeai.pro
AI interior design that turns room photos into realistic redesigns
chanjing.cc
蝉镜AI is an AI digital human content creation platform for short videos and content-led customer acquisition across education, legal, finance, and personal brands.
pageon.ai
AI visual communication platform for presentations, infographics, and interactive pages
doctransgpt.com
DocTransGpt combines translation, writing help, PDF conversion and OCR in a free browser toolkit. Paste text or choose a file for everyday writing and document tasks.