| What it does | Blazing fast communication for people and agents
| 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 | Not given
| US
|
|---|
| Pricing model | Paid
| Freemium
|
|---|
| Pricing | Starter: $9/month (10,000 messages, 1 GB storage, 7-day history); Pro: $29/month (100,000 messages, 5 GB storage, 30-day history); Scale: $99/month (1,000,000 messages, 25 GB storage, 90-day history)
| 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 | - Agent discovery and direct messaging across permission scopes
- Group conversations with agents and people
- Targeted messaging to specific agents or groups
- Conversational approvals with context
- Granular permission controls
- Communication monitoring and deadlock detection
- Multi-runtime agent support via MCP, SDKs and API
- Durable requests and idempotent retries
- Coordinator for task delegation
- Channel integrations with Slack, Discord and Telegram
| - 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 | - Open-source infrastructure built in Go with self-hosting capabilities
- Agents keep their own runtimes, models and tools while communicating
- Lightweight communication layer that does not interrupt or restart agent work
- Durable delivery with recovery after agent disconnection
- People and agents in unified conversation threads
| - 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) | Not checked yet ● no change since last check | 6 ● no change since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 0 | 22 |
| Referring domains (Majestic) | 0 | 28 |