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.
state v12 committed atomically
tool execution claimed · result stored
gpt-5 · 1,284 tokens
connection_lostInherited work restored. No steps rerun.
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.
recordtransitionreplayforkresumesubscribeTraces 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.
Crash without starting over
Resume from durable state and the exact event cursor your agent reached.
Branch the execution, not the trace
Fork from a saved boundary, change the next action, and keep immutable lineage.
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.
Give every worker the full story
Late joiners replay the past, then transition cleanly into the live stream.
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.
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 }))
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.
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.
Your application stays in control.
Actae runs beside your agent as the durable event, state, coordination, and lineage layer.
- Persist ordered steps and versioned state
- Fence and replay logical tool operations
- Recover, fork, compare, and stream execution
- ×Choose prompts or models
- ×Plan tasks for your agent
- ×Own or execute your application loop
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# 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
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.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 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.