Infrastructure agent · governed by the plan
Turf is a drop-in replacement for Terraform® that lets an AI agent operate your infrastructure — governed by the artifact your team already trusts. Every change is planned, visible, and approved before it happens. Nothing runs off-plan.
the Terraform plan becomes the agent’s TODO list — worked one effect at a time
That instinct is correct — and it’s exactly the problem Turf is built around.
An agent holding raw cloud credentials mutates infrastructure with no diff, no review, and no state — the same failure mode as console click-ops, only faster.
The governing instrument is the industry-standard Terraform plan. Turf constrains the agent to work in terms of plans and their effects. Nothing runs off-plan.
Every proposed change is visible before it happens, gated on your approval, and applied one effect at a time — with room to pause, back up, or re-plan.
AI does the work. The plan keeps it honest. Here’s the loop every Turf change goes through.
Natural language, a diagram, or Terraform HCL — desired state always lands in a reviewable configuration directory.
Turf produces a standard Terraform plan. Its effects become the agent’s TODO list — it can’t act outside them.
Humans and policy checks sign off on the plan. Nothing crosses the gate without approval and clearance.
There is deliberately no apply_all. Between effects the agent can pause,
take a backup, or ask for help.
Deferred work — the CRD that didn’t exist yet — loops back through a fresh plan until the graph settles.
↻ step 5 feeds back into step 2 — every round crosses the approval gate again
Turf is a drop-in replacement — your configs, your modules, your providers, your mental model. With agentic superpowers on top.
Turf is an independent product built on the OpenTofu framework — not affiliated with or endorsed by HashiCorp.
cluster → operators → CRDs → workloads. no -target hacks, no two-stage applies.
turf up iterates plan → approve → apply until your infrastructure
matches intent — including the layers Terraform makes you deploy in awkward stages.
Cluster + addons (operators, CRDs) + workloads (manifests, Helm charts) in one converging deploy. Deferrals bridge the “CRD doesn’t exist yet” gap natively.
Remote state backends, policy checks, private module registries, org skills — Turf slots into your Terraform automation platform. Complement, not rip-and-replace.
run it yourself →Governance isn’t just for deployments. Failovers, rotations, upgrades run as Terraform Actions — planned, approved, and executed under the same gate as everything else.
run it yourself →Plan-gated approval, effects as a TODO list. The agent acts only with approval and clearance.
turf up converges the whole graph across phases — with Actions and
first-class deferrals that OpenTofu doesn’t have.
Compose policy into plan approval — OPA policy checks, cloud best practices — through your security vendors’ MCP servers. Org- and provider-specific skills encode your rules.
provider skills — coming soonA second set of eyes with semantic knowledge: Turf knows replacing a stateful resource destroys data — and takes backups, seeks approval, or proposes a safer plan.
Start with plots — agent-authored, reviewable HCL. Build on
registry modules. Promote to idiomatic .tf when you’re ready to shift left.
GitOps, planning, approval, and execution are building blocks — compose them in novel ways. Plan locally, approve in CI, commit what converged — not one rigid commit → PR → plan → apply pipeline.
planfile round-trip — coming soonOne engine, many surfaces — Turf is an MCP server first.
chat, up, destroy, execModel flexibility is a governance feature, not a checkbox.
turf --model dmr/ai/qwen3 — no API key, no cost--base-urlYour infrastructure intent never has to leave your network.
We’re looking for design partners — teams working on layered infrastructure, policy gates, and AI under real governance constraints. Partner with us early: white-glove onboarding, direct roadmap influence, and discounted commercial terms while we build together.