| What it does | Platform to build and run AI agents across tools, browser, and Android phone with human approval on every action
| Real-time steering and guardrails for AI agents
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Sandbox free, Outpost $20/month, Forge $49/month ($469/year with 20% discount), Bastion $129/month ($1,239/year with 20% discount), Citadel starts at $490/month for enterprise
| Team: Free per organization, unlimited users, 200 session-hours per month. Enterprise and Gateway: Custom pricing, billed annually.
|
|---|
| Key features | - Visual builder for multi-agent workflows
- Support for 8,446+ tools across web, code, data, and operations
- 111+ subagent templates with 16 prebuilt crews
- Device Control for Android app automation
- Browser Control for web automation
- Human-in-the-loop approval on every consequential action
- Support for multiple AI models including Claude, GPT, Gemini, and local models
- MCP Server integration with Claude, ChatGPT, and Cursor
- Full replay and audit logs for every run
- Per-workflow RAG with vector and static context
| - Reads every tool call agents make and blocks unsafe ones before they run
- Catches stalled and runaway sessions while they run
- Steers agents back when they go past what was asked
- Tracks every session's tokens against usual usage
- Stops credential and data leaks before they leave the machine
- Inventories all agents, MCP servers and skills in use
- Blocks dangerous calls before they run in agent hooks and at the gateway
- Sends every finding to Slack, webhook or SIEM
- Verifies each agent's identity before access
- Keeps audit-grade masked records of every action and decision
|
|---|
| What makes it different | - Human approval on every consequential action enforced by platform
- No API integrations needed for Android and web automation
| - Works with Claude Code, Codex, Cursor, Devin and more
- Runs on your machines, gateways and in the cloud
- Active steering corrects or stops drifting runs
- One policy applied across all MCP servers, plugins and skills
- Continuously monitors components for known vulnerabilities
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 28 ▲ +1 (up) since last check | 3 ▲ +2 (up) since last check |
|---|
| Trust Flow (Majestic) | 21 | 13 |
|---|
| Citation Flow (Majestic) | 27 | 25 |
|---|
| Referring domains (Majestic) | 121 | 23 |
|---|
Melaya
Stacktrace