Connection lost
Trying to reconnect…
Server didn't respond
Recovering…
Documentation
Docs
Install a runner, author packs, wire in an LLM. The full reference and example packs live in the GitHub repo .
Get started
Operate
Policies & approvals
Risk-tier defaults, per-action overrides, human approvals, and revocable standing grants — control what runs.
Read it
Runbooks
Saved, versioned action sequences — policy-gated per step, readable by your LLM as playbooks.
Read it
Teams & access
Roles, invitations, per-member runner scopes, account-wide MFA, sessions, and API key scopes.
Read it
Runner fleet
Groups and labels, enrollment keys, pack credentials, updates, troubleshooting, and clean removal.
Read it
Audit & SIEM
What gets recorded, the dashboard view, NDJSON export with a read-only key, and the runner journal.
Read it
Build packs
Reference
Security model
Trust boundary, searchable cloud audit, hash-chained runner journal, redaction-before-egress.
Read it
Hosting & plans
The supported product is the hosted emisar control plane today; the source-available repo can be evaluated in your own environment. Plans and audit retention are on the pricing page.
Read it
Use cases
Worked examples of letting an agent operate real infrastructure through declared, gated, audited actions — not a shell.
Cassandra ops
Triage a read-latency alert and run nodetool repair on the lagging keyspace, behind one approval.
Read it
Postgres ops
Check replication lag and slow queries, then terminate a blocking backend — with approval.
Read it
Incident response: the 33-hour wipe
A CSI driver reformats a live volume; the agent contains it through declared actions and writes the fix to Terraform.
Read it
Stuck on something?
Open an issue on GitHub or email us. We answer fast.