Skip to content
mast is folding into core-agent and is frozen (2026-10-30). The current release is v0.10.0, the last feature release; there is no 1.0. go-steer now has one agent harness; mast's capabilities are landing in core-agent as features (tracking). Decision: #596. New work starts in core-agent. See the roadmap.

mast

Agent infrastructure for unattended, library-embedded, multi-provider, durable workloads — built for platform and SRE teams.

Is mast for you? Thirty seconds of honesty

Section titled “Is mast for you? Thirty seconds of honesty”

As of 2026-10-30, the answer is: use core-agent. It is the one harness go-steer maintains; it already runs unattended on a cluster with approval gates, budgets, durable sessions and remote attach; and everything that made mast different — the durable write gate and outbox, the spend ledger, the scheduling lease, workload bundles and specialists, A2A, the monitoring cycle, the AX task-runner deployment — is landing there (go-steer/core-agent#1411). Pick mast only if you already run it and are waiting on a specific port. The cards below describe the job mast was built for, which is now core-agent’s job.

You're a platform team

Agents in Cloud Run, GKE, scheduled jobs, or compiled into your own services — incident triage, runbook automation, monitoring. You’re home. Start with the quickstarts below.

You're embedding an agent in a Go service

mast composes as a library, not just a binary. You get the same governance code the daemon runs — gate, outbox, ceilings, watchdog — and bring your own trigger, with a CI-enforced slim-embed guarantee so you pay for what you import.

You want one simple agent loop

Use raw ADK v2 — no governance, no durability, smallest possible surface. Come back when the loop must survive restarts, needs budget or permission governance, needs provider switching, or stops having a human watching it.

  1. Unattended. Runs without a human watching: HTTP-triggered workloads, budget ceilings, and approvals that wait for an operator instead of failing.
  2. Library-embedded. Composes as a Go library inside larger services — with a tested slim-embed guarantee: pay for what you import.
  3. Multi-provider. Same config switches models without code changes — Gemini (with Google Search and URL-context builtins), Claude on the first-party API or Vertex, and offline test models. Your own backend goes in through mast.Config.Model, which is covered by the v1.0 promise.
  4. Durable. Sessions live in SQLite or Postgres and survive process death — a paused approval outlives kill -9 and resumes in a fresh process.

Nothing changes your cluster without an operator

Section titled “Nothing changes your cluster without an operator”

A specialist that would change something stops before the call fires, shows the operator the tool and its arguments, and waits — durably, across a restart. That boundary is structural rather than prompt-held: a specialist declares whether it may change anything, and mast refuses to start a roster in which a read-only one can reach a mutating tool.

Then read the concepts — how workloads, dispatch, durability, approvals, budgets, tools and providers fit together — or why mast exists if you want the argument before the API.

mast is the lean sibling of core-agent — same org, different job. The full design corpus lives in the repo under docs/.