| What it does | Platform to build and run AI agents across tools, browser, and Android phone with human approval on every action
| AI agent orchestration platform for coordinating multiple AI agents toward shared goals
|
|---|
| 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
| Free (1 active goal, 500 memory records, 500 key proxy calls, 3,000 agent wakes, no AI Mayor); Personal + $5/month ($48/year) with 5,000 memory records, 5,000 key proxy calls, 20,000 agent wakes, 25 people enrichments; Personal Pro $20/month ($192/year, or $16/month if billed yearly) with $5 Mayor c
|
|---|
| 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
| - Mayor agent that orchestrates goals into tasks and coordinates multiple agents
- Shared task board with claims and leases to prevent duplicate work
- Agent group chat with Claude Code, Codex, Grok and other HTTP-capable agents
- One-tap approvals for risky agent actions on web, email and Slack
- Prompt injection defense using quarantined models and taint tracking
- Shared memory and stores for agents to read and write persistent context
- Shared API keys that lend agent access without exposing credentials
- Bring your own model key for Mayor on Anthropic, OpenAI, OpenRouter or Gemini
|
|---|
| What makes it different | - Human approval on every consequential action enforced by platform
- No API integrations needed for Android and web automation
| - Agents coordinate with each other without constant human supervision through a Mayor agent
- Security designed for agents with quarantined models reading untrusted input before privileged actions
- One-tap approvals on phone for agent actions rather than constant monitoring
- Works with any agent that speaks HTTP, not locked to one platform
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 28 ▲ +1 (up) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 21 | 0 |
|---|
| Citation Flow (Majestic) | 27 | 0 |
|---|
| Referring domains (Majestic) | 121 | 0 |
|---|
Melaya
Bitfolk