Skip to content
New Lumen 2.0 & the durable Agent Runtime

Ship agents
that think.

Lumen is the AI-native platform for building, tracing and deploying production agents. Go from prompt to planet-scale in seconds, not sprints.

Free forever for side projects · No credit card

Trusted by 14,000+ teams shipping agents

Running in production at 14,000+ teams, from seed-stage to Fortune 100

  • Halcyon
  • Northbeam
  • Orbital
  • kestrel
  • Meridian
  • Parallax
  • nimbus
  • Quanta

Platform

One platform for every layer of the agent stack.

Runtime, memory, tools, evals and observability, designed together, so your agents are fast, safe and boring to operate.

Runtime

Durable agents that survive anything.

Checkpointed, resumable runs with automatic retries, branching and human-in-the-loop pauses, out of the box.

Inference

312 regions. One endpoint.

Requests route to the nearest warm GPU automatically.

38msp50 TTFT

312edge regions

Evals

Regressions never ship.

Continuous evals gate every deploy against your real traffic.

Memory

Semantic memory, built in.

Vector recall with TTLs, scopes and per-user isolation.

Traces

Traces you can actually read.

Every prompt, tool call and token, replayable step by step.

Registry

MCP-native tool registry.

400+ typed, permissioned tools. Bring your own in one line.

Guardrails

Governance without the drag.

PII redaction, injection shields and hard spend caps, enforced at the edge.

Deploy

Push to deploy. Live before you blink.

Immutable versions, atomic traffic shifts and one-click rollbacks. No containers to babysit.

8.2s median push → live

  1. Build

    1.8s

  2. Evals

    2.4s · 248/250

  3. Replicate

    3.1s · 312 regions

  4. Live

    0.9s · traffic 100%

How it works

From idea to production in three moves.

Stage 01 / 03
  1. 01

    Connect

    Point Lumen at your models, data and tools. The MCP-native registry gives every agent typed, permissioned access in a single line.

  2. 02

    Compose

    Wire steps into a durable graph. Lumen compiles it into a checkpointed runtime with retries, branching and human approval built in.

  3. 03

    Deploy

    Push once. Lumen ships to 312 edge regions in under ten seconds, with traces, evals and rollbacks switched on from the very first request.

Developers

Write agents like you write code.

Typed SDKs for TypeScript and Python. A CLI that feels instant. A runtime that gets out of your way.

  • Local-first dev server with hot-reloading agents
  • Git-native deploys with a preview URL for every PR
  • OpenTelemetry-compatible traces, exported anywhere
  • Deterministic replays: debug any run, step by step
Read the docs

$ lumen init support-agent
✔ Scaffolded support-agent (TypeScript · 14 files)
$ lumen dev
▲ Dev server ready on http://localhost:4200 41ms
$ lumen deploy
◇ Building 1.8s
◇ Running evals 248/250 passed (99.2%)
◇ Replicating 312 regions
✔ Live at https://support-agent.lumen.run · 8.2s
$

2.4B

agent runs / month

Orchestrated on Lumen across 14,000+ production teams.

38ms

median time-to-first-token

Global p50, measured from 312 edge regions.

312+

edge regions

Deploy once. Run within 40 ms of 96% of the world’s users.

99.99%

uptime, contractually

Backed by a financially guaranteed SLA on Scale.

Customers

Teams that ship faster sleep better.

We replaced eleven microservices and a homegrown orchestrator with Lumen in a single sprint. Our support agent now resolves 63% of tickets end-to-end, and I finally sleep through on-call.

Priya Raman

VP Engineering, Halcyon

63% tickets auto-resolved

The traces alone are worth it. I can replay any failed run, step by step, and see exactly which tool call went sideways.

Marcus Feld

Staff Engineer, Northbeam

−71% MTTR

Deploys in eight seconds. I timed it. Twice. Then I made the whole team watch.

Aiko Tanaka

Founder, Kestrel

8.2s deploys

Evals as a deploy gate changed how we ship. Regressions get caught long before a customer ever sees them.

Daniel Okoye

Head of AI, Meridian

0 regressions in Q2

Latency dropped from 2.1s to 380ms after we moved inference to the edge. We didn’t change a line of code.

Tom Whitaker

CTO, Parallax

2.1s → 380ms

Lumen is the first platform that treats agents like real distributed systems: checkpoints, retries, idempotency. It’s boring in exactly the right ways.

Sofia Lindqvist

Principal Engineer, Orbital

40M runs / month

We evaluated five platforms. Lumen was the only one our security team approved on the first pass.

Grace Adeyemi

CISO, Quanta

SOC 2 · HIPAA

Pricing

Start free. Scale without surprises.

Pay for agent runs, not seats. Every plan includes traces, evals and the full runtime.

Monthly Annual Save 20%

Spark

For side projects and first experiments.

$0 / month

Free forever · no card

Start for free
  • 10,000 agent runs / month
  • 1 project, shared edge region
  • 7-day trace retention
  • Community support
Most popular

Pro

For teams running agents in production.

$39 / month $49

Billed annually · $468/yr

Start 14-day trial
  • 500,000 agent runs / month
  • Unlimited projects · 50 regions
  • Continuous evals & deploy gates
  • 30-day traces & deterministic replay
  • Priority support · 4h response

Scale

For organisations with serious traffic.

$199 / month $249

Billed annually · $2,388/yr

Talk to us
  • 10M agent runs / month
  • All 312 regions · private networking
  • SSO / SAML & audit logs
  • 1-year retention · 99.99% SLA
  • Dedicated Slack channel

Need VPC deployment, data residency or a custom SLA? Talk to sales →

FAQ

Questions, answered.

Still stuck? Our engineers answer in minutes, not days.

Talk to an engineer

Lumen is an AI-native platform for building, running and observing production agents. It bundles a durable runtime, semantic memory, a tool registry, continuous evals and global inference behind one SDK and one deploy command.

Any of them. Lumen is model-agnostic: bring your own keys for the major providers, use open-weight models we host on our edge GPUs, or mix them per step with automatic fallbacks and cost-aware routing.

Agents compile to lightweight, snapshot-based sandboxes that are pre-warmed across 312 regions. A deploy pushes a new immutable version and shifts traffic atomically, so there are no cold builds and no container registry round-trips.

Never. Prompts, traces and memory are encrypted in transit and at rest, isolated per project, and never used to train any model. Bring-your-own-cloud and regional data residency are available on Scale.

Yes. Enterprise customers can run the data plane in their own AWS, GCP or Azure account, or on-prem, while Lumen manages the control plane. Talk to us about air-gapped deployments.

Nothing breaks. Agents keep running and overage is billed at a transparent per-run rate, with hard budget caps you control. You’ll get alerts at 70%, 90% and 100% of your quota.

Ready when you are

Your agents are waiting.

Start free in under a minute. No credit card, no sales call, no cold starts.