Trinity

The deciding trait is the schedule. Agents here run on cron, which means the useful boring work, the dependency sweep, the nightly check, the report nobody writes, happens while you are asleep rather than while you are watching. That changes what you are willing to hand over, because nothing has to fit in your attention.

You are the wrong buyer if you want to supervise every step, because the design assumes you will not be there. Pick it for recurring work. Pick a session manager for the work you want to watch.

The credential design is the flaw. Secrets are stored encrypted inside the repository that versions agent state, so every key ever used remains in history under a key that also has to live somewhere. Rotation does not remove the old value, a clone carries the whole archive, and the encryption is only as good as the one secret nobody rotated.

What it does right is give every agent its own container. Isolation is per agent rather than per installation, which is the correct granularity for a fleet.

1. Two mechanisms do the work here. An audit trail described as tamper-evident makes after-the-fact reconstruction meaningful rather than merely available, and an escalation queue gives an autonomous run a defined point at which a person must act. 2. Together they turn unattended execution into something reviewable, which is the precondition for trusting it at all.

2. No evaluation is published and none is claimed, so the argument is structural. The structure is the strongest on this row.

There is a company here, which already separates it from most of this cohort, and there is a marketplace, which tells you where the revenue is meant to come from. Give away the orchestration, take a position in the ecosystem that grows on top of it. 506 stars is early for that strategy and the strategy is sound.

Moat: the marketplace, if it fills. Likely acquirer: a platform vendor wanting scheduled agents without building the control plane. Position: the most investable project in this cohort, and I would want to see the marketplace populated before believing the second half.

Spend is tracked in the product, health is monitored across the fleet, and each agent is contained separately, which are three of the four things I normally have to build myself. Self-hosting means the data question answers itself and the cost is infrastructure my team already runs.

The fourth thing is identity: no SSO, no SCIM, and nothing mapping an action to a person in my directory. Sixty engineers sharing a fleet without that is an attribution gap. Approved with conditions: identity integration on the roadmap in writing, and a spend ceiling per agent.

The endpoint is the reason I would run this. Over ninety tools are exposed at a single path, so the agent I already use becomes the operator: listing the fleet, starting a conversation with one of them, changing a schedule, all from the client I already have configured. That is composition instead of another console to learn.

Apache-2.0 and a self-hosting path that is a clone, a copy of an example environment file and one script. The models are vendor-hosted, which is the one part not mine.