Durable runtime infrastructure for agents

Durable execution for
long-running AI agents.

Recover after crashes, retry tools without duplicating side effects, and fork from saved state without rerunning the past.

Managed Cloud or self-hosted Python, Go & TypeScript PostgreSQL Private beta
support-agent / run_8f31 LIVE
EXECUTION TIMELINEcursor 0048
00:01.2 · CURSOR 0045Customer context loaded

state v12 committed atomically

00:02.8 · CURSOR 0046Refund policy verified

tool execution claimed · result stored

00:04.1 · CURSOR 0047Response composed

gpt-5 · 1,284 tokens

PROCESS EXITEDconnection_lost
ACTAE RECOVERYResume from cursor 0047

Inherited work restored. No steps rerun.

01

Your agent should not forget an hour of work because one worker died.

Processes restart. Networks time out. Tool results arrive ambiguously. A trace can explain the loss. Actae gives the application the durable state and execution history needed to continue.

One API for the execution lifecyclerecordtransitionreplayforkresumesubscribe
BUILT FOR CONSEQUENCE

Traces tell you what happened.
Actae lets you continue.

Observability is useful after the fact. Autonomous software also needs operational memory while it runs: durable state, ordered events, idempotent work, and exact recovery boundaries.

RECOVER

Crash without starting over

Resume from durable state and the exact event cursor your agent reached.

01
FORK

Branch the execution, not the trace

Fork from a saved boundary, change the next action, and keep immutable lineage.

02
RETRY SAFELY

Do not perform the side effect twice

Claim tool operations with leases and stable keys. Replay a stored result or fence a stale worker instead of sending, charging, or writing twice.

03
COORDINATE

Give every worker the full story

Late joiners replay the past, then transition cleanly into the live stream.

04
PAST → PRESENT

Every participant arrives fully caught up.

A new worker, dashboard, evaluator, or approval agent can replay durable history from any cursor and move into live delivery without a race or a hand-built handoff.

“I need every participant to have immediate access to both the past and the present.”
execution.tsCONNECTED
1 await actae.record(channel, event)
2 await actae.transition(event, state)
3
4 // recover history, then stay live
5 for await (event of actae.stream({ cursor }))
Replaycursor 0 → 47
Syncno event gap
Livecursor 48 →
YOUR STACK, STILL YOURS

Bring the framework.
Keep control of execution.

Actae does not choose prompts, models, or tools. It makes the facts of execution durable underneath the stack you already use.

LANGGRAPHLANGCHAINCLAUDEOPENAICODEXCOPILOTPYTHONGOTYPESCRIPT

One deployable system

Ordered event log, versioned state, live WebSockets, consumer coordination, and execution lineage behind one endpoint.

Choose the boundary

Use a dedicated managed Cloud runtime for zero operations or self-host Actae when execution data must remain in your infrastructure.

Evidence, not screenshots

Fork receipts and causal histories connect the outcome to the exact boundary, state, tools, and decisions that produced it.

HOW IT FITS

Your application stays in control.

Actae runs beside your agent as the durable event, state, coordination, and lineage layer.

ACTAE DOES
  • Persist ordered steps and versioned state
  • Fence and replay logical tool operations
  • Recover, fork, compare, and stream execution
ACTAE DOES NOT
  • ×Choose prompts or models
  • ×Plan tasks for your agent
  • ×Own or execute your application loop
CLOUD OR SELF-HOSTED

One execution model. Your deployment boundary.

Start with a dedicated managed Cloud endpoint, or run the same commercial Actae runtime in your infrastructure when data residency or network control requires it. The private beta is founder-assisted and does not carry a public availability SLA.

Discuss your deployment
actae-runtimeLICENSED
# place the supplied binary on your host
$ chmod +x ./actae

# enroll this installation
$ ./actae enroll <enrollment-key>

# start the self-hosted runtime
$ ./actae --config ./actae.toml
Licensed runtime operationalself-hosted data plane
PRIVATE BETA

Build the right durable runtime with us.

Actae Cloud is currently founder-assisted. Tell us about one agent workflow, its reliability requirements, and where you need to run it. We will help you choose Cloud or self-hosted Actae.

Contact us at hello@actae.dev Pricing and self-service checkout will open after the private beta.
OPERATED IN THE OPEN

Private beta, stated plainly.

Actae Cloud has isolated tenant runtimes, PostgreSQL control-plane recovery tooling, usage guardrails, component health reporting, and operational alerts. It does not yet claim a public SLA or General Availability.

Live service healthCustomer-visible component status refreshes every 30 seconds.View current status

GA gates remain explicitMulti-node recovery, PostgreSQL HA, an external security review, formal on-call ownership, and measured margins must be evidenced before GA.Review security posture

MAKE EXECUTION DURABLE

Make one agent run survive a crash.

Bring one workflow that already runs for 10+ minutes. We will review the architecture, provision a dedicated Cloud endpoint or a self-hosted evaluation, and help you prove recovery.

Contact us Book architecture review