| What it does | The approval layer for AI agents
| AI agent orchestration platform for coordinating multiple AI agents toward shared goals
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Open Source: free and self-hosted. Free: $0/month hosted plan with up to 5 members. Scale: $20 per user per month. Enterprise: Custom annual contract.
| 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 | - Tool call interception for all agent frameworks
- Automatic approval rules to prevent fatigue
- AI judge for complex rule evaluation
- Works with LangGraph, CrewAI, Mastra, Claude Agent SDK and more
- Open Agent Approval Protocol for framework independence
- Self-hosted or cloud-hosted deployment options
- Custom permission policies and organization controls
| - 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 | - Framework-agnostic: works with any AI agent through the open Agent Approval Protocol
- No vendor lock-in: open source spec and SDKs let you swap providers without rewriting agents
- Comprehensive audit trail for accountability and compliance
- Meets reviewers where they work with multi-platform notifications
- Policy-based routing to eliminate approval bottlenecks
| - 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) | 30 ▼ −1 (down) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 6 | 0 |
|---|
| Citation Flow (Majestic) | 28 | 0 |
|---|
| Referring domains (Majestic) | 48 | 0 |
|---|
withHuman
Bitfolk