| What it does | AI agent orchestration platform that models workflow with triggers, actors, stages, gates, permissions, and outcomes
| Action governance for AI agents that enforces policy on every tool call, command, and query before it executes
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2025
|
|---|
| Based in | US
| US
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Not given
| Community: Free (1,000 scans/month); Pro: $99/month (25,000 scans/month); Team: $499/month (150,000 scans/month); Enterprise: Custom pricing
|
|---|
| Key features | - Role-based organization with humans or AI agents in any position
- Workflow definitions with triggers, stages, gates, and outcomes
- Agent-agnostic design supporting Claude, Codex, Gemini, and local models
- Scoped credentials with least privilege access per stage
- Deterministic gates for tests, reviews, and approvals
- Audit trail with hash-chained tamper-evident ledger
- Local-first deployment with optional cloud hosting
- Isolated git worktrees for independent work and verification
- Budget tracking and spend monitoring per organization
- Separation of duties enforced in code
| - 9-layer cognitive pipeline for threat detection
- Real-time policy enforcement on tool calls and agent actions
- Agent scope declaration with purpose, tools, and expiry
- Human-in-the-loop approval workflows
- Session-aware correlation across multi-turn conversations
- Compliance reporting mapped to SOC 2, HIPAA, GDPR, PCI DSS, ISO 27001
- Multiple deployment options: Cloud SaaS, VPC, air-gapped, sovereign
- Six integration channels: REST API, MCP, LLM Gateway, Python, TypeScript, Go SDKs
- Deterministic pattern checks in under 15 milliseconds
- Adversarial testing with 6,500+ in-house pattern variants
|
|---|
| What makes it different | - Orchestration layer that treats work as executable processes rather than remembered habits or wikis
- Roles swappable between humans and AI agents without rewriting workflows
- Credentials and secrets held by infrastructure, never exposed to AI models
- Autonomous AI decision-making within defined stages, deterministic controls at stage boundaries
| - Independent governance outside the AI model vendor's control
- Evidence of every decision mapped to compliance frameworks without reconstruction
- Fail-closed default: agent stops when Shrike cannot make a decision
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 22 ▲ +2 (up) since last check | 6 ● no change since last check |
| Trust Flow (Majestic) | 7 | 0 |
| Citation Flow (Majestic) | 31 | 22 |
| Referring domains (Majestic) | 18 | 28 |