Launched this week
Managed agent as a service: launch a long-horizon AI agent in one click — Claude Code, Codex, Hermes, or OpenClaw — with full history, managed recovery, and access through WhatsApp, iMessage, Telegram, Slack, web, API developers, and CLI.
The cross-channel part is the most compelling to me. If the same long-running agent can keep context across Slack, Telegram, CLI, and web without each app team rebuilding the plumbing, that removes a lot of hidden operational work. Curious how you think about audit logs for those handoffs over time.
AgentSky
@senlin_wang Thanks! Right now we provide limited activity logs in our system, but we are developing more profound logging support.
The cross-platform memory is the part I’m most curious about. If a user starts debugging a problem through Discord, then continues the conversation through email or a support portal later, does the agent maintain the same context and history, or does each channel create an isolated session?
For developer communities, users rarely stay on one platform, so I’m wondering how agents handle context continuity when conversations move across different channels.
AgentSky
@new_user___176202668afdbb135b4f71f
> If a user starts debugging a problem through Discord, then continues the conversation through email or a support portal later,
The conversation will be continuous for AgentSky agents.
Congrats on the launch! 👏
How does AgentSky handle failed or partially completed tasks? can an agent resume from its previous state instead of starting over?
AgentSky
@fletcher_oliver Thanks! We snapshot context sessions while agent is running. If an agent crashed, it will resume from previous snapshot, not starting over.
how does pricing work when an agent is parked but still maintaining its state? is there any cost for storage, snapshots or backups while it is inactive?
AgentSky
@rivendell_chorro We use a ultra low cost solution for parked agent state. So there will be hot restore and cold restore based on the agent activeness. There will be cost for storage in general, as long as the agent had created artifacts that is in ours system.
I like that AgentSky puts different models and agent tools in one place. It could save a lot of time when testing ideas, especially for people who don’t want to set up everything themselves. I’d still like to see more real examples before using it for a bigger project.
AgentSky
@letitia00 Thanks! Yes, quickly experimenting across different harness/LLM combinations was one of our pain points in the past, that is why we think others may need this too. We have hosted more than 10k agent sessions already in real products.
How do the evals work on model comps?
AgentSky
@zrk222 Eval is coming soon in next few days!
Triforce Todos
Love the pay-only-when-working model, that's a smart pricing call.
Curious how you're handling security across sandboxes when agents are running always-on like that?
AgentSky
@abod_rehman Great question! The agents are not always on in AgentSky, they suspend/resume base on work load. The sandboxes are based on MicroVM so that it is secure by standard and also fast to boot. Is there any particular security concern your product may care about?