agentgate
Active·★ 33·MIT·Updated 2026-10-11
AgentGate is a human-in-the-loop approval system that empowers users to maintain control over AI agent actions. It defines policies to auto-approve safe actions, auto-deny dangerous ones, and routes ambiguous requests to humans via various channels like Slack or a dashboard.
#AI Agents#Human-in-the-Loop#Policy Engine#Approval Workflow#API Gateway#Workflow Automation#Security#Observability
01
Features
01Policy engine for auto-approval, auto-denial, or human routing
02Multi-channel approvals via Slack, Discord, email, or web dashboard
03Full audit trail for every request, decision, and action
04Docker-ready for easy self-hosting of the full stack
05Production-hardened with SSRF protection, ReDoS defense, and structured logging
02
Compatibility
Docker
Containerization
Verified via docs
TypeScript
Language
Verified via docs
PostgreSQL
Database
Verified via docs
SQLite
Database
Verified via docs
03
Quick start
1
$ docker compose up
04
Use cases
↳Controlling sensitive AI agent actions like sending emails, deleting files, or deploying code.
↳Enforcing compliance and governance over AI agent operations by defining approval policies.
↳Integrating human decision-making into any AI agent framework using the provided SDK or MCP.
↳Providing a centralized dashboard for reviewing, approving, or denying pending agent requests.
05
Alternatives
BubbleLab★ 1.1k
Open source workflow automation platform built for developers - full observability and code exportability!
ProxmoxMCP-Plus★ 610
Use MCP and OpenAPI to safely control Proxmox VE VMs, LXCs, backups, and snapshots from LLMs and AI agents.
pingfusi★ 131
MCP server + CLI that puts a real human in your coding agent's loop. It publishes work mid-task, a reviewer pins what's wrong and returns a verdict, and the agent iterates until approved.
Comments
Log in to leave a comment
No comments yet. Be the first!