Real-time
Live pulse rates and ordered stream state from operational heartbeats—incidents, tickets, deploys, pipeline stages—agents subscribe to under MCP policy once your kickoff workspace is live.
Kickoff puts organizational heartbeats on a governed mesh for multi-horizon agent BI — not a chat seat trial. Start with live ops; expand knowledge & analytics as they ship; use free local MIT memory when recall matters.
Full organizational heartbeat: live operations, knowledge memory, and analytics patterns — department-scoped, policy-gated. Kickoff is the onboarding path into that same fabric: activate a workspace, connect heartbeats, and give agents governed multi-horizon context from day one.
Standing up ops heartbeats feeds multi-horizon intelligence with honest readiness. You pay for workspaces, connectors, and usage on the mesh floor—not a per-seat chatbot that forgets operational truth.
Live pulse rates and ordered stream state from operational heartbeats—incidents, tickets, deploys, pipeline stages—agents subscribe to under MCP policy once your kickoff workspace is live.
Hours to days of stream history and rolling operational context across systems. Not first-class 1h/24h/7d aggregate products as GA SKUs during onboarding.
Analytical history (Beta) plus free local MIT memory for institutional patterns—seasonality, RCA themes, and durable recall under tenancy as your mesh matures.
One fabric, three signals: live operations, knowledge, and analytics — department-scoped, policy-gated.
Tickets, incidents, deploys, and customer updates, organized by team. The primary heartbeat a reviewer can see after a source, a stream, and a signed event.
Docs, runbooks, and memory of past heartbeats. What previous activity meant. Reviewers can open this layer in the product; do not chip it as a readiness label.
Patterns and trends across heartbeats so agents see beyond the moment. Same rule: describe the layer, do not chip a status.
Broker mesh floor
1 workspace + 1 connector + 25 GiB · adjust up on pricing
Local memory
$0
TUI + kernel + memory-mcp on your machine
Pricing model
Usage-based
Start small, prove value, then scale meters