The governed agent runtime and control plane for AI work#
AI agents are powerful — but deploying them into real workflows without guardrails is a liability. When an agent modifies data, commits code, sends a message, or triggers a workflow, you need to know what happened, who approved it, and whether it followed policy.
LumenFlow is the governed agent runtime and control plane that sits between AI agents and the actions they take. Teams often start with software delivery because it is the clearest enterprise wedge, but the same runtime also powers Sidekick and connected agents in other workflow domains. It enforces policy, routes risky work through approvals, and keeps an exportable evidence trail of everything.
Product map#
LumenFlow is one governed runtime with three product surfaces and two commercial motions:
| Surface | Who it serves | Entry point | |
|---|---|---|---|
| Sidekick | Governed AI assistant | Consumers, operators | Sign up, chat, delegate |
| Connected Runtimes | External agent governance | Developers, platform teams | SDK enrollment, heartbeat, dispatch |
| Software Delivery | AI dev workflow control | Engineering teams | Kernel install, gates, evidence |
These surfaces share one runtime, one policy engine, one evidence store, and one approval model. The commercial motions are:
- B2C — Sidekick expands demand by making AI useful in everyday workflows
- B2B — Connected runtimes and delivery deepen enterprise value and retention
- The reinforcing loop: consumer demand makes integrations more valuable; business integrations make consumer outcomes harder to replace
What users can now do on LumenFlow Cloud#
Users can now create, launch, supervise, approve, recover, and audit multi-agent work from the cloud. Mission Control is the operator surface for launching and supervising governed work, while Studio shows the live mission graph, safe actions, approvals, artifacts, and replay evidence.
In practical terms, teams can:
- launch governed Sidekick or agent missions without spawning a local terminal process for supported flows
- approve risky actions from the workspace, mobile surfaces, or connected channel surfaces
- inspect who acted, what policy applied, what budget decision fired, and what replay evidence was saved
- connect external runtimes so existing agents report heartbeat, events, evidence, and health into the same control plane
- rely on durable worker scheduling for routines, hosted runtime launches, and wakeups rather than treating cron as the only progress mechanism
The product is still governed by workspace policy and rollout flags. LumenFlow does not grant agents unbounded access to tools or data; every connected action still runs through the configured approval, budget, evidence, and replay boundaries.
How it works#
| Layer | What it does |
|---|---|
| Policy | Define rules for what agents can do autonomously vs. what requires review |
| Approvals | Route risky actions through human or automated approval gates |
| Evidence | Every action is logged with full context — who, what, when, why |
| Export | Audit trails are exportable for compliance, review, and incident response |
Kernel and Cloud#
LumenFlow ships in two forms:
- Kernel — the open-source enforcement layer you embed in your development workflow. It validates agent actions against policy locally.
- Cloud — the hosted control plane that adds team visibility, approval routing, evidence storage, and export across your organization.
You can start with the kernel alone and add Cloud when you need cross-team governance.
Core principles#
- Policy before execution — agents propose, rules decide
- Evidence by default — every action produces a proof trail
- Human-in-the-loop where it matters — escalation for risky work, autonomy for safe work
- Open architecture — bring your own models, tools, and runtimes
info LumenFlow is in beta. We're building in public and shipping fast. Your feedback shapes the product.
Next step#
Head to Architecture Overview to see how the kernel, cloud, and governed surfaces fit together.